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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    c
    1.06
    t
    1.03
    p
    0.95
    g
    0.93
    0.91
    नी
    0.90
    dı
    0.89
    d
    0.88
    не
    0.84
     crux
    0.84
    POSITIVE LOGITS
     fórmulas
    1.23
     fórmula
    1.14
    Formula
    1.11
    1
    1.03
    0
    1.02
     formules
    0.98
    formula
    0.96
    ோ
    0.94
    that
    0.93
    formulas
    0.93
    Act Density 0.012%

    No Known Activations