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

    Neuronpedia

    INDEX
    Explanations

    position

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GetData
    -0.08
    viously
    -0.07
    ఆ
    -0.07
     away
    -0.07
    Needs
    -0.07
    Sell
    -0.07
    迮
    -0.07
    .Output
    -0.07
    팸
    -0.06
    ipeg
    -0.06
    POSITIVE LOGITS
     الفرنسي
    0.08
     Wolves
    0.07
    (recipe
    0.07
     الرابع
    0.07
    cnt
    0.06
    ">&#
    0.06
     ply
    0.06
     navy
    0.06
    pring
    0.06
     соответств
    0.06
    Act Density 0.093%

    No Known Activations