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
     означа
    -0.07
    Categories
    -0.07
    .fillRect
    -0.06
     myšlen
    -0.06
    Bar
    -0.06
    /about
    -0.06
     devised
    -0.06
    ラック
    -0.06
    这样
    -0.06
     Save
    -0.06
    POSITIVE LOGITS
    -contrib
    0.07
    /exp
    0.07
     ULONG
    0.07
     Over
    0.07
     contributes
    0.06
    _dep
    0.06
    ecial
    0.06
     over
    0.06
    -post
    0.06
     punct
    0.06
    Act Density 0.049%

    No Known Activations