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

    Neuronpedia

    INDEX
    Explanations

    being alive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ন
    1.04
    ن
    1.04
    ޏ
    1.02
     кислоты
    0.98
    ল
    0.95
    eris
    0.94
     limitaciones
    0.93
    of
    0.91
     exploración
    0.91
    লভ
    0.91
    POSITIVE LOGITS
     alive
    1.45
     Alive
    1.33
    2
    1.23
    '
    1.08
    4
    1.04
    Alive
    1.01
     by
    0.95
    AY
    0.86
    3
    0.86
    .
    0.85
    Act Density 0.002%

    No Known Activations