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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash

    instances of intra-word punctuation and compound/abbreviated forms (e.g., hyphenations, slashes, underscores, and contractions) within phrases.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
     downloads
    -0.07
    앙
    -0.07
     attacking
    -0.07
     lapse
    -0.06
    _touch
    -0.06
    subtotal
    -0.06
     regulation
    -0.06
    (vo
    -0.06
     varies
    -0.06
     phi
    -0.06
    POSITIVE LOGITS
    getName
    0.07
    nodeName
    0.07
    ScreenState
    0.06
    Inicial
    0.06
    coef
    0.06
    Seek
    0.06
    .TextAlign
    0.06
     onClose
    0.06
     знаком
    0.06
    (ps
    0.06
    Act Density 0.019%

    No Known Activations