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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ir
    1.60
    uously
    1.14
     पंत
    1.12
     hardness
    1.09
     exasper
    1.09
    ument
    1.09
    eligible
    1.08
     presentato
    1.08
     médiocrement
    1.08
     ziel
    1.07
    POSITIVE LOGITS
    𝑖
    1.00
    بت
    0.98
     संस्कारों
    0.97
    లే
    0.96
    ানার
    0.96
     fring
    0.95
    तंत्र
    0.94
    নাথ
    0.93
    日本の
    0.92
    кона
    0.92
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.