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

    Neuronpedia

    INDEX
    Explanations

    research studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Component
    -0.07
    京
    -0.07
     coding
    -0.07
    .Strict
    -0.07
    페이지
    -0.06
     Typ
    -0.06
    636
    -0.06
     western
    -0.06
     ascii
    -0.06
     crochet
    -0.06
    POSITIVE LOGITS
     dern
    0.06
    관련
    0.06
     irq
    0.06
    _removed
    0.06
    urchased
    0.06
     actionTypes
    0.06
    weeted
    0.05
    _agg
    0.05
     asym
    0.05
     небольш
    0.05
    Act Density 0.026%

    No Known Activations