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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UARIO
    -0.07
     rewards
    -0.06
     embraced
    -0.06
     Bundesliga
    -0.06
    Franc
    -0.06
    ana
    -0.06
    战争
    -0.06
     خواهند
    -0.06
     関
    -0.06
    ورن
    -0.06
    POSITIVE LOGITS
     المه
    0.07
     dug
    0.07
    석
    0.07
     compromising
    0.07
     обличчя
    0.07
     folding
    0.07
     driveway
    0.07
    속
    0.06
     ๆ
    0.06
    .previous
    0.06
    Act Density 0.006%

    No Known Activations