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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    از
    -0.06
     ses
    -0.06
     최신
    -0.06
     чор
    -0.06
    ESSAGE
    -0.06
     fün
    -0.06
    ाप
    -0.06
     Nearly
    -0.06
     storms
    -0.06
    MERCHANTABILITY
    -0.06
    POSITIVE LOGITS
     우리
    0.07
    )<<
    0.06
     шк
    0.06
    ifton
    0.06
    dbg
    0.06
     Unc
    0.06
    ="-
    0.06
     BOOL
    0.06
    ा:
    0.06
     commentator
    0.06
    Act Density 0.042%

    No Known Activations