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

    Neuronpedia

    INDEX
    Explanations

    using namespace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.84
    ες
    0.79
    s
    0.75
    p
    0.75
     skeptical
    0.73
    ྥ
    0.73
     Honourable
    0.73
     sensual
    0.72
     foreseeable
    0.71
     identically
    0.71
    POSITIVE LOGITS
    溘
    0.88
     amerikan
    0.85
     ausgewählt
    0.82
     Uri
    0.82
    ენტის
    0.79
     mögliche
    0.79
     américaine
    0.79
     форми
    0.77
     Ré
    0.76
     amerikanischen
    0.76
    Act Density 0.000%

    No Known Activations