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

    Neuronpedia

    INDEX
    Explanations

    cause and effect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ని
    1.06
    ך
    1.03
    。
    1.01
    <h4>
    0.97
    ра
    0.96
     начало
    0.95
    сет
    0.95
    <h5>
    0.94
     služ
    0.91
    다
    0.91
    POSITIVE LOGITS
    of
    1.23
    er
    1.16
    ig
    1.16
    id
    1.05
    u
    1.05
    ers
    1.00
    st
    0.95
    b
    0.93
    ed
    0.93
    ade
    0.92
    Act Density 0.037%

    No Known Activations