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

    Neuronpedia

    INDEX
    Explanations

    News and media

    np_max-act · gemini-2.0-flash

    The neuron lights up on non‐functional, content‐bearing words—particularly nouns and adjectives that carry concrete or technical meaning.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    REAL
    -0.07
     Arab
    -0.07
     亚洲
    -0.07
    开
    -0.06
    IEW
    -0.06
     Shiite
    -0.06
    western
    -0.06
    sources
    -0.06
     Bitcoin
    -0.06
    !(
    -0.06
    POSITIVE LOGITS
     Juni
    0.07
    されている
    0.07
     QVBoxLayout
    0.06
    ('',
    0.06
    ()));
↵
    0.06
     ragaz
    0.06
    _params
    0.06
     NavLink
    0.06
     combineReducers
    0.06
    ندية
    0.06
    Act Density 0.408%

    No Known Activations