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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _MAG
    -0.06
     italic
    -0.06
     mafia
    -0.06
    35
    -0.06
     avis
    -0.06
     TKey
    -0.06
    _spaces
    -0.06
     guitars
    -0.06
    _glyph
    -0.06
    -0.06
    POSITIVE LOGITS
    .evaluate
    0.08
    confidence
    0.07
     Hort
    0.07
     Percent
    0.06
    .getBoolean
    0.06
    Object
    0.06
    +="
    0.06
     regardless
    0.06
    (define
    0.06
    [--
    0.06
    Act Density 0.012%

    No Known Activations