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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الأسهم
    -0.08
    黄瓜
    -0.07
    职工
    -0.07
    海关
    -0.07
     lifes
    -0.07
    Signing
    -0.06
    item
    -0.06
     compliments
    -0.06
    那位
    -0.06
    修理
    -0.06
    POSITIVE LOGITS
    нат
    0.06
    ую
    0.06
    .getMap
    0.06
    DOCTYPE
    0.06
    ዩ
    0.06
    Seattle
    0.06
     способ
    0.06
    であろう
    0.06
     Daw
    0.06
     Но
    0.06
    Act Density 0.010%

    No Known Activations