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

    Neuronpedia

    INDEX
    Explanations

    landmark law, case, agreement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.21
     as
    1.14
    是
    1.03
    는
    0.95
    は
    0.93
    కు
    0.89
     То
    0.75
     Соб
    0.69
    เป็น
    0.68
     %.
    0.68
    POSITIVE LOGITS
    م
    0.95
    ir
    0.79
    ور
    0.68
    raises
    0.68
    की
    0.65
    ری
    0.65
     in
    0.64
    urence
    0.64
    ury
    0.63
    ara
    0.63
    Act Density 0.001%

    No Known Activations