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

    Neuronpedia

    INDEX
    Explanations

    signal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     outlines
    -0.07
    _extractor
    -0.07
     Overall
    -0.06
    _race
    -0.06
     dried
    -0.06
    坊
    -0.06
    equality
    -0.06
    تك
    -0.06
    -toggler
    -0.06
    .Point
    -0.06
    POSITIVE LOGITS
    ियल
    0.07
     itemBuilder
    0.06
    _indicator
    0.06
    (update
    0.06
    iều
    0.06
    SJ
    0.06
    ै,
    0.06
    chai
    0.06
     Holder
    0.06
     beware
    0.06
    Act Density 0.003%

    No Known Activations