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

    Neuronpedia

    INDEX
    Explanations

    UTF-8 encoding declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gold
    0.41
    她在
    0.40
    セント
    0.39
    Mac
    0.39
    Gold
    0.39
    Sa
    0.38
    Jess
    0.38
     წინ
    0.38
    hehi
    0.38
     joueurs
    0.38
    POSITIVE LOGITS
     densities
    0.39
     বিদ্যমান
    0.39
    ตรา
    0.36
    ercicio
    0.36
     fasting
    0.35
    ᚕ
    0.35
     teórico
    0.35
     ângulo
    0.35
    രിക
    0.35
    एशन
    0.34
    Act Density 0.001%

    No Known Activations