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

    Neuronpedia

    INDEX
    Explanations

    partial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     teg
    -0.07
     være
    -0.07
     cui
    -0.07
    ukkan
    -0.07
    appable
    -0.07
    📏
    -0.06
    come
    -0.06
     uży
    -0.06
    فرنس
    -0.06
    揕
    -0.06
    POSITIVE LOGITS
     Dist
    0.08
    (Card
    0.07
    address
    0.07
    Lost
    0.07
     freight
    0.07
     equitable
    0.07
    カード
    0.07
    道路
    0.07
     Frm
    0.07
    多项
    0.07
    Act Density 0.000%

    No Known Activations