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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     IData
    -0.07
    lection
    -0.07
    員
    -0.06
    _feats
    -0.06
    _slope
    -0.06
    igmoid
    -0.06
    widgets
    -0.06
    _dropout
    -0.06
    Threshold
    -0.06
     dojo
    -0.06
    POSITIVE LOGITS
     України
    0.07
     autof
    0.07
     Asi
    0.07
     wrote
    0.07
    Apache
    0.07
     ситуа
    0.07
    -cap
    0.07
    方向
    0.07
     आल
    0.06
    ены
    0.06
    Act Density 0.019%

    No Known Activations