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

    Neuronpedia

    INDEX
    Explanations

    typical examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AudioFocus
    0.90
    шена
    0.80
    anol
    0.79
     regalos
    0.77
    ହା
    0.73
    ަމ
    0.72
     ऐलान
    0.71
     etiam
    0.71
     ଯ
    0.71
     dukkham
    0.69
    POSITIVE LOGITS
     typical
    4.58
    Typical
    4.27
    typical
    4.19
     Typical
    4.13
    典型
    3.43
     типи
    3.31
    典型的
    3.24
     típico
    3.18
     típica
    3.13
     representative
    2.73
    Act Density 0.460%

    No Known Activations