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

    Neuronpedia

    INDEX
    Explanations

    on + state descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    র
    0.80
    제로
    0.80
    ДО
    0.78
     успі
    0.73
    た
    0.73
    شک
    0.73
    لی
    0.73
    ি
    0.71
    Т
    0.71
     vutto
    0.70
    POSITIVE LOGITS
    are
    0.73
    ı
    0.72
    na
    0.68
    iv
    0.67
    et
    0.64
    0.64
     an
    0.63
    if
    0.63
    ne
    0.63
     MIMO
    0.60
    Act Density 0.001%

    No Known Activations