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

    Neuronpedia

    INDEX
    Explanations

    the full, artwork, name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    n
    0.81
    لا
    0.76
    ار
    0.74
    EN
    0.74
    s
    0.72
    יו
    0.72
     А
    0.71
    را
    0.70
    ام
    0.70
    ম
    0.70
    POSITIVE LOGITS
     utilização
    0.80
    żli
    0.76
    datal
    0.74
     sérieux
    0.74
    دة
    0.73
    asının
    0.73
     véritable
    0.72
     необходимо
    0.72
    .?
    0.72
    ويل
    0.72
    Act Density 0.802%

    No Known Activations