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

    Neuronpedia

    INDEX
    Explanations

    script/dialogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ophage
    -0.08
     निकाल
    -0.07
     sway
    -0.07
     opvol
    -0.07
    发展的
    -0.07
     propagated
    -0.07
     ocorrer
    -0.07
     Buc
    -0.07
     zhv
    -0.07
     fabr
    -0.07
    POSITIVE LOGITS
     guys
    0.10
     yourselves
    0.09
     yeah
    0.09
     감사합니다
    0.09
    🏼
    0.08
     genial
    0.08
     please
    0.08
     Aussie
    0.08
     thoughts
    0.08
     really
    0.08
    Act Density 0.345%

    No Known Activations