Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    academic achievement

    np_max-act · gemini-2.0-flash

    information related to the production processes of various chemical compounds.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron responds to words that signal a degree or quality qualifier—e.g. honors, distinction, small margin, thin stream, high purity—marking terms that qualify or measure something.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -way
    -0.07
    けて
    -0.07
    디
    -0.06
    otify
    -0.06
    ”的
    -0.06
     tvoří
    -0.06
    사가
    -0.06
     그렇
    -0.06
    entialAction
    -0.06
     Dry
    -0.05
    POSITIVE LOGITS
    201
    0.07
     darf
    0.07
    .Nome
    0.07
    _license
    0.07
    obierno
    0.06
    Reporter
    0.06
    ami
    0.06
    202
    0.06
     hindsight
    0.06
     energie
    0.06
    Act Density 0.165%

    No Known Activations