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

    Neuronpedia

    INDEX
    Explanations

    over

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Navbar
    -0.07
     influencers
    -0.07
     intelligence
    -0.07
    ܨ
    -0.07
    eling
    -0.07
    {n
    -0.07
    全国人大
    -0.06
    Feb
    -0.06
     Average
    -0.06
     Pulitzer
    -0.06
    POSITIVE LOGITS
    .Void
    0.07
    .CompareTo
    0.07
     toll
    0.07
    وع
    0.07
    곡
    0.07
     kindly
    0.07
    /icon
    0.07
    所做的
    0.06
    也不要
    0.06
    垢
    0.06
    Act Density 0.350%

    No Known Activations