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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     noticeably
    -0.08
    保驾护
    -0.07
    需要注意
    -0.07
    /mL
    -0.07
    _ENTER
    -0.07
    晦
    -0.07
    *np
    -0.07
    _VE
    -0.07
    新年
    -0.07
     engraved
    -0.07
    POSITIVE LOGITS
    ʞ
    0.09
    قط
    0.07
     인간
    0.07
    ument
    0.07
     compat
    0.07
    pred
    0.07
     produção
    0.07
    坨
    0.07
    strument
    0.07
     independ
    0.07
    Act Density 0.018%

    No Known Activations