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

    Neuronpedia

    INDEX
    Explanations

    explore esoteric or occult influences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;\
    1.15
    сти
    1.01
    ।'
    0.99
    。
    0.99
    。\
    0.98
     परंतु
    0.98
    但在
    0.95
     αλλά
    0.93
    ح
    0.93
    ।
    0.93
    POSITIVE LOGITS
    or
    0.98
    Y
    0.93
    ၉
    0.93
    l
    0.92
    U
    0.90
    IEnumerable
    0.88
    ITH
    0.86
    inburgh
    0.85
    AR
    0.84
    ாதி
    0.84
    Act Density 0.460%

    No Known Activations