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

    Neuronpedia

    INDEX
    Explanations

    female

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    king
    -0.06
     ～
    -0.06
    	where
    -0.06
     tố
    -0.06
    wap
    -0.06
    가를
    -0.06
     *,↵
    -0.06
    ्पर
    -0.06
    rench
    -0.06
    頃
    -0.06
    POSITIVE LOGITS
    prevState
    0.07
    snapshot
    0.07
    _VOLUME
    0.07
     Doğu
    0.06
     aes
    0.06
     plist
    0.06
    ensemble
    0.06
    .Identifier
    0.06
    esian
    0.06
    Wiki
    0.06
    Act Density 0.003%

    No Known Activations