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

    Neuronpedia

    INDEX
    Explanations

    Learning math

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     discrep
    0.90
    ренные
    0.88
    рены
    0.86
     bandwagon
    0.85
    ändige
    0.85
    бовать
    0.82
     ganglia
    0.81
     Debye
    0.80
    রাষ্ট্রে
    0.80
     tamar
    0.79
    POSITIVE LOGITS
     (
    0.72
    lus
    0.67
    stable
    0.65
    cs
    0.64
    עות
    0.63
    cycle
    0.62
     memer
    0.62
     état
    0.61
     règle
    0.61
     છું
    0.61
    Act Density 0.002%

    No Known Activations