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

    Neuronpedia

    INDEX
    Explanations

    legal, social, and technical concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anesi
    0.46
     and
    0.42
     також
    0.42
    嗕
    0.42
     પરંતુ
    0.40
    istere
    0.39
     Survey
    0.39
    orre
    0.39
    ณ
    0.39
    oleh
    0.38
    POSITIVE LOGITS
     creatinine
    0.46
     ček
    0.42
     precies
    0.42
     actuales
    0.41
     variación
    0.40
     déchir
    0.39
     générations
    0.39
     différentes
    0.39
     cá
    0.39
     waiters
    0.39
    Act Density 0.025%

    No Known Activations