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

    Neuronpedia

    INDEX
    Explanations

    new

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ash
    -0.07
    VOID
    -0.07
    -view
    -0.07
     Covered
    -0.07
    愚蠢
    -0.07
    .World
    -0.07
    _ROUT
    -0.07
    IEW
    -0.07
    udo
    -0.07
    Mate
    -0.07
    POSITIVE LOGITS
    pięt
    0.07
    (if
    0.07
    have
    0.07
    Pie
    0.07
    ¥
    0.07
     Choosing
    0.07
    adder
    0.07
    _documents
    0.06
    电磁
    0.06
    (lambda
    0.06
    Act Density 0.061%

    No Known Activations