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

    Neuronpedia

    INDEX
    Explanations

    senior/junior

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     affiliates
    -0.07
     nach
    -0.06
    细胞
    -0.06
    -Agent
    -0.06
     borrowed
    -0.06
     Shipping
    -0.06
    �i
    -0.06
    _import
    -0.06
     governments
    -0.06
    的话
    -0.06
    POSITIVE LOGITS
     tách
    0.07
    istinguish
    0.07
    xAD
    0.07
     Ре
    0.06
     overlooked
    0.06
    rosso
    0.06
    іє
    0.06
    _like
    0.06
     TForm
    0.06
     repmat
    0.06
    Act Density 0.006%

    No Known Activations