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

    Neuronpedia

    INDEX
    Explanations

    XML namespace prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    g
    1.93
    er
    1.84
    se
    1.77
    ie
    1.75
    y
    1.73
    a
    1.71
    am
    1.65
    en
    1.64
    to
    1.60
    k
    1.60
    POSITIVE LOGITS
     sete
    1.42
     ocen
    1.42
     domen
    1.31
     Baru
    1.27
    IN
    1.25
     laureate
    1.25
     måtte
    1.23
     coral
    1.21
     Trabal
    1.21
     sello
    1.19
    Act Density 0.000%

    No Known Activations