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

    Neuronpedia

    INDEX
    Explanations

    org. identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⭓
    -2.78
    ྄
    -2.61
    珰
    -2.61
    躄
    -2.56
    vantaged
    -2.55
    鲞
    -2.38
    稣
    -2.36
    mbgg
    -2.34
    苼
    -2.34
    archiwizowane
    -2.33
    POSITIVE LOGITS
    "
    3.17
    ية
    2.70
    —
    2.63
    j
    2.48
    .,
    2.45
    At
    2.45
     =
    2.41
    In
    2.30
    The
    2.30
    te
    2.19
    Act Density 0.004%

    No Known Activations