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

    Neuronpedia

    INDEX
    Explanations

    crimes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Flam
    -0.07
    ic
    -0.07
    (sess
    -0.06
    _swap
    -0.06
    Changes
    -0.06
     Tyson
    -0.06
     conte
    -0.06
     level
    -0.06
     Preis
    -0.06
     Cres
    -0.06
    POSITIVE LOGITS
    ONGLONG
    0.07
     vac
    0.06
     jsem
    0.06
    ASN
    0.06
    는다
    0.06
    стор
    0.06
    )e
    0.06
     blinded
    0.06
    啊
    0.06
    ,j
    0.06
    Act Density 0.013%

    No Known Activations