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

    Neuronpedia

    INDEX
    Explanations

    consumer research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cook
    -0.06
    -begin
    -0.06
     čer
    -0.06
     wo
    -0.06
     hạn
    -0.06
    rió
    -0.06
    amment
    -0.06
    晴
    -0.06
    ')]
    -0.06
     Mush
    -0.06
    POSITIVE LOGITS
    시오
    0.08
     ↵        ↵
    0.07
    _RESP
    0.07
    ↵   ↵
    0.07
     IRepository
    0.07
    filename
    0.06
     potvr
    0.06
    克斯
    0.06
    overflow
    0.06
    िं
    0.06
    Act Density 0.034%

    No Known Activations