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

    Neuronpedia

    INDEX
    Explanations

    Structures/elements

    np_max-act · gemini-2.0-flash

    This neuron activates on technical nouns describing structured, repeating physical components or surface patterns (e.g. grooves, corrugations, lenticular elements, cells).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Regular
    -0.08
    ///////////////////////////////////////////////////////////////////////////////↵
    -0.07
     coating
    -0.07
     regression
    -0.07
    snippet
    -0.06
    _object
    -0.06
    comfort
    -0.06
    エル
    -0.06
    Speed
    -0.06
    cm
    -0.06
    POSITIVE LOGITS
     jMenuItem
    0.07
    ／／／／／／／／
    0.07
    .enum
    0.06
     podrob
    0.06
     mend
    0.06
    τήσεις
    0.06
    álie
    0.06
     detach
    0.06
    웨디시
    0.06
    .datas
    0.06
    Act Density 0.036%

    No Known Activations