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

    Neuronpedia

    INDEX
    Explanations

    before or after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     klar
    0.43
     which
    0.42
     أحمد
    0.41
     للغاية
    0.41
    which
    0.38
     figli
    0.38
     calculateur
    0.38
     karet
    0.38
     ireo
    0.38
     scroll
    0.38
    POSITIVE LOGITS
    доступ
    0.53
    एं
    0.49
     среди
    0.49
    opolymers
    0.48
     மட்டுமே
    0.48
    ？」
    0.48
    ویه
    0.48
    だけでなく
    0.47
    выше
    0.47
    லை
    0.45
    Act Density 0.001%

    No Known Activations