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

    Neuronpedia

    INDEX
    Explanations

    Code/Scraper text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <|endoftext|>
    -0.11
    <|reserved_200016|>
    -0.08
     Suzanne
    -0.08
    inne
    -0.08
    ores
    -0.08
    āc
    -0.07
    ତ
    -0.07
     Louisiana
    -0.07
     statewide
    -0.07
    腾讯
    -0.07
    POSITIVE LOGITS
     הדברים
    0.07
    _PM
    0.07
    ారం
    0.07
     товар
    0.07
    tritt
    0.07
    /Event
    0.07
    [attr
    0.06
     rail
    0.06
    tridge
    0.06
    0.06
    Act Density 12.693%
    No Known Activations