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

    Neuronpedia

    INDEX
    Explanations

    special characters and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    toare
    0.89
    ق
    0.83
    ని
    0.77
    un
    0.75
    rational
    0.74
    もら
    0.74
    toadd
    0.72
    ri
    0.71
     Hinweis
    0.70
    depends
    0.70
    POSITIVE LOGITS
    ك
    1.19
    .
    1.11
    ai
    1.04
    z
    0.98
    ്യ
    0.97
    ี
    0.90
    ne
    0.88
     juin
    0.88
     .
    0.87
     de
    0.85
    Act Density 0.000%

    No Known Activations