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
     promise
    -0.06
    @",
    -0.06
     everything
    -0.06
     fatal
    -0.06
    찌
    -0.06
    +S
    -0.06
     ﾞ
    -0.06
    _arrays
    -0.06
     zdraví
    -0.06
     Ke
    -0.06
    POSITIVE LOGITS
    Suffix
    0.06
    vern
    0.06
     كل
    0.06
     بشكل
    0.06
     Thương
    0.06
    _traj
    0.06
     Func
    0.06
     مختلف
    0.06
     представ
    0.06
    صول
    0.06
    Act Density 0.172%

    No Known Activations