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

    Neuronpedia

    INDEX
    Explanations

    specifying duration or manner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SHUNT
    0.95
     защиту
    0.91
     asignar
    0.91
     conformado
    0.88
     ilan
    0.88
    ClFN
    0.86
     эт
    0.83
     annan
    0.83
     establecida
    0.82
     понятия
    0.81
    POSITIVE LOGITS
    n
    1.01
    ن
    0.96
    nö
    0.95
    ህ
    0.93
    біль
    0.89
    حة
    0.89
    어
    0.88
    nın
    0.87
    앤
    0.87
    nä
    0.86
    Act Density 0.000%

    No Known Activations