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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    鸰
    0.85
    𝒶
    0.78
    RUNTIME
    0.75
    ৭
    0.75
    ‌آ
    0.75
    स्त्र
    0.73
     आंकड़ा
    0.73
     administer
    0.72
     respiratoires
    0.72
    𝓇
    0.72
    POSITIVE LOGITS
    .
    0.92
     Однако
    0.91
     しかし
    0.89
     But
    0.84
    на
    0.84
    But
    0.84
    কিন্তু
    0.82
    ן
    0.80
    ты
    0.80
    다라고
    0.80
    Act Density 0.648%

    No Known Activations