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

    Neuronpedia

    INDEX
    Explanations

    NPR transcripts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _VAL
    -0.07
     قطع
    -0.07
     Peach
    -0.07
    ад
    -0.07
     Flam
    -0.06
    DOUBLE
    -0.06
    려
    -0.06
     confused
    -0.06
    :"",↵
    -0.06
    %p
    -0.06
    POSITIVE LOGITS
     NPR
    0.07
    (headers
    0.06
    BLOCK
    0.06
    claimed
    0.06
     реб
    0.06
     trx
    0.06
     dinh
    0.06
     monoc
    0.06
    زم
    0.06
    $action
    0.06
    Act Density 0.010%

    No Known Activations