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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    威尔
    -0.09
    _SAMPL
    -0.07
    bew
    -0.07
     DIFF
    -0.07
    (Dialog
    -0.07
     Wig
    -0.07
     Stephen
    -0.07
     tasting
    -0.07
    /K
    -0.07
     John
    -0.07
    POSITIVE LOGITS
    hasOne
    0.08
    🛸
    0.07
    CTX
    0.07
    --------↵↵
    0.07
    招收
    0.07
     ר
    0.07
    出会い系
    0.07
    记录
    0.07
    vd
    0.07
    ashington
    0.07
    Act Density 0.013%

    No Known Activations