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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     extraordinaire
    1.37
    zelfde
    1.34
    ం
    1.32
    o
    1.27
    faits
    1.23
    かは
    1.20
    leşt
    1.19
    ी
    1.17
     avions
    1.17
    िमा
    1.16
    POSITIVE LOGITS
     probabilidad
    1.06
     bang
    1.04
    Diagnosis
    0.99
    ется
    0.97
    ޕ
    0.95
    ют
    0.95
    abilistic
    0.95
     প্রতি
    0.94
    يرات
    0.94
    aces
    0.93
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.