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

    Neuronpedia

    INDEX
    Explanations

    brains and thinking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iliary
    -0.07
     spotting
    -0.06
     beams
    -0.06
     Bor
    -0.06
    im
    -0.06
    pdo
    -0.06
     Rousse
    -0.06
    ,args
    -0.06
     voice
    -0.06
    antha
    -0.06
    POSITIVE LOGITS
     кого
    0.07
    詳細
    0.06
    思
    0.06
     find
    0.06
    ImageContext
    0.06
    )))))↵
    0.06
    Discount
    0.06
     fkk
    0.06
     NOT
    0.06
     чет
    0.06
    Act Density 0.161%

    No Known Activations