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

    Neuronpedia

    INDEX
    Explanations

    class

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Boxing
    -0.08
     boxing
    -0.08
    [table
    -0.08
     volunt
    -0.07
    อาจาร
    -0.07
    炉
    -0.07
     redhead
    -0.07
    �
    -0.07
     Nodo
    -0.07
     nIndex
    -0.07
    POSITIVE LOGITS
    共建
    0.07
    'C
    0.07
    写
    0.07
     win
    0.07
    ctica
    0.07
    选择
    0.07
    _CHANNELS
    0.06
    него
    0.06
    icit
    0.06
    /reset
    0.06
    Act Density 0.045%

    No Known Activations