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

    Neuronpedia

    INDEX
    Explanations

    adverbs of degree

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اعمال
    -0.60
    GEBURTSDATUM
    -0.60
    forChild
    -0.57
     Administrativna
    -0.56
     ImportError
    -0.54
    anskje
    -0.54
     partag
    -0.54
    Välislingid
    -0.53
     Hidup
    -0.53
     democracia
    -0.52
    POSITIVE LOGITS
     sendi
    0.57
     inconven
    0.56
     convinced
    0.56
     involved
    0.56
     aware
    0.55
     persuaded
    0.55
     fascinated
    0.52
     interested
    0.51
     enam
    0.51
    帖最后由
    0.48
    Act Density 0.011%

    No Known Activations