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

    Neuronpedia

    INDEX
    Explanations

    extinguish

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ok
    -0.07
     hayata
    -0.07
    ////
    -0.07
     beer
    -0.07
    <D
    -0.06
     Αρχ
    -0.06
     <|
    -0.06
     加
    -0.06
     malloc
    -0.06
     bras
    -0.06
    POSITIVE LOGITS
     extinction
    0.09
     extingu
    0.08
    USH
    0.07
    ct
    0.07
    ISH
    0.07
    unched
    0.07
    نت
    0.06
    OTHER
    0.06
     Out
    0.06
    .Name
    0.06
    Act Density 0.003%

    No Known Activations