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

    Neuronpedia

    INDEX
    Explanations

    books and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    I
    0.62
    S
    0.61
    B
    0.60
    E
    0.59
    P
    0.59
    ’
    0.59
    all
    0.58
     when
    0.57
    m
    0.57
    L
    0.57
    POSITIVE LOGITS
    <unused2019>
    0.55
    𒅴
    0.54
    湎
    0.54
     Políticas
    0.52
    𒀸
    0.52
     фаразлары
    0.51
     ouvrage
    0.51
    ꗧ
    0.51
     ఆదాయ
    0.50
    뷌
    0.50
    Act Density 0.001%

    No Known Activations