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

    Neuronpedia

    INDEX
    Explanations

    apologize

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [ch
    -0.08
     Current
    -0.07
     stock
    -0.07
     volunteered
    -0.07
    /GL
    -0.06
    esses
    -0.06
    ﾓ
    -0.06
    𡐓
    -0.06
    (const
    -0.06
    char
    -0.06
    POSITIVE LOGITS
    礼仪
    0.07
    宴会
    0.07
     affair
    0.07
    ping
    0.06
    想要
    0.06
    🧤
    0.06
    Subscriber
    0.06
    舐
    0.06
     foundation
    0.06
    国际化
    0.06
    Act Density 0.011%

    No Known Activations