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

    Neuronpedia

    INDEX
    Explanations

    Greek letters and escaping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     knotted
    0.42
    nearest
    0.40
    bind
    0.39
    jord
    0.39
     thống
    0.38
    survey
    0.37
    ುತ್ತೇನೆ
    0.37
     Vir
    0.37
    hips
    0.37
    stripped
    0.37
    POSITIVE LOGITS
    噪声
    0.41
     triumphs
    0.39
     न्यूज़
    0.39
     positifs
    0.38
    トル
    0.38
    Cm
    0.38
     μέσα
    0.38
     آج
    0.37
    Noise
    0.37
    Вакансия
    0.37
    Act Density 0.003%

    No Known Activations