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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    о
    1.06
    rinth
    1.03
    roscopic
    0.99
     кажу
    0.99
    €™
    0.98
     swirling
    0.98
    defs
    0.92
    urbs
    0.89
    кси
    0.86
    மதி
    0.86
    POSITIVE LOGITS
    ように
    1.45
     रहता
    1.44
     रहती
    1.40
     cuantos
    1.39
     готовы
    1.34
     custodia
    1.33
    不
    1.32
     protiv
    1.31
     Surely
    1.31
     successivo
    1.29
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.