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

    Neuronpedia

    INDEX
    Explanations

    structures and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    C
    0.75
    O
    0.70
    过
    0.68
     а
    0.61
    A
    0.60
    我
    0.60
     от
    0.59
    Q
    0.58
     over
    0.58
    Το
    0.58
    POSITIVE LOGITS
    宗旨
    0.68
     Sociales
    0.62
     ন্যায্য
    0.56
    n
    0.55
    stown
    0.54
    zinho
    0.54
    nDims
    0.53
    prices
    0.52
     MER
    0.52
    notlocked
    0.52
    Act Density 0.000%

    No Known Activations