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

    Neuronpedia

    INDEX
    Explanations

    spirit of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    1.27
    í
    1.20
    ان
    1.12
    ма
    1.11
    ت
    1.11
    ри
    1.08
    сти
    1.04
    ת
    1.04
    ı
    1.02
    ся
    1.01
    POSITIVE LOGITS
    spirit
    1.28
     a
    1.13
    ר
    1.13
     spirit
    1.05
     Espíritu
    0.98
     Бүген
    0.98
     ३
    0.97
    Spirit
    0.96
     encamp
    0.95
     Toutefois
    0.95
    Act Density 0.006%

    No Known Activations