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

    Neuronpedia

    INDEX
    Explanations

    intensity in coding contexts

    np_max-act · gemini-2.0-flash

    code and error handling related to web development and programming concepts.

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

    The neuron responds to descriptive evaluative adjectives (e.g. “careless,” “great,” “dirty”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    てい
    -0.06
    .Room
    -0.06
    食べ
    -0.06
    ann
    -0.06
    変わ
    -0.06
    рип
    -0.06
     우리는
    -0.06
    itta
    -0.06
    -framework
    -0.06
    ynn
    -0.06
    POSITIVE LOGITS
    (private
    0.07
    中华
    0.06
     realidad
    0.06
    ває
    0.06
    072
    0.06
     東京
    0.06
    Incoming
    0.06
     عضو
    0.06
     चर
    0.06
     Marks
    0.06
    Act Density 0.203%

    No Known Activations