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

    Neuronpedia

    INDEX
    Explanations

    drawing, paths, and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     இ
    0.60
     Wells
    0.58
    iksi
    0.55
     ఇం
    0.54
    ך
    0.53
    کن
    0.52
    ʳ
    0.52
    مال
    0.52
     RIA
    0.51
    ించ
    0.51
    POSITIVE LOGITS
    त्रा
    0.71
     sentimento
    0.64
    érences
    0.63
     impass
    0.63
    макра
    0.62
    ascape
    0.58
     ascended
    0.58
     plexus
    0.58
    xiety
    0.58
    ብ
    0.58
    Act Density 0.199%

    No Known Activations