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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ла
    0.78
     wildest
    0.69
    🆈
    0.68
    quele
    0.68
     đương
    0.68
    ᠩ
    0.67
    КА
    0.66
    т
    0.66
    ຕົວ
    0.66
    用に
    0.65
    POSITIVE LOGITS
    s
    1.28
     was
    0.97
    m
    0.93
    ES
    0.92
    I
    0.84
     a
    0.83
    ss
    0.79
    ma
    0.78
     in
    0.77
    if
    0.77
    Act Density 0.014%

    No Known Activations