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

    Neuronpedia

    INDEX
    Explanations

    uncertainty and placeholders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     impoverished
    0.70
     excreted
    0.69
    辱
    0.65
    ähn
    0.62
     malfunction
    0.60
     dụng
    0.59
     ExifInterface
    0.59
     ingested
    0.58
     kullanımı
    0.57
     mediante
    0.57
    POSITIVE LOGITS
     uncertainties
    1.38
     uncertainty
    1.38
     uncertain
    1.24
     undecided
    1.23
     অনিশ্চ
    1.23
    uncertain
    1.20
     incertid
    1.17
     Uncertainty
    1.16
     Uncertain
    1.09
     vague
    1.02
    Act Density 0.449%

    No Known Activations