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

    Neuronpedia

    INDEX
    Explanations

    long-term initiative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     combattre
    1.21
     tumult
    1.20
    牛肉
    1.20
     puris
    1.20
     パンツ
    1.19
     库存
    1.18
     rapporto
    1.16
    로운
    1.15
    SMA
    1.12
    زمت
    1.12
    POSITIVE LOGITS
    ala
    1.03
     TestCase
    0.98
    ativer
    0.97
     lima
    0.97
     Submission
    0.95
     wesentlich
    0.95
    pictureBox
    0.94
     Shot
    0.94
    обходи
    0.93
    0.93
    Act Density 0.000%

    No Known Activations