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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     benches
    0.44
    ْب
    0.42
     dealership
    0.42
     pockets
    0.42
     dissent
    0.41
     THAN
    0.41
     Chihuahua
    0.41
    м
    0.40
    ቸውን
    0.39
     amu
    0.39
    POSITIVE LOGITS
     fluide
    0.49
    气候
    0.48
    คับ
    0.48
    heden
    0.48
    lanır
    0.47
    razi
    0.47
    वाइड
    0.46
     iako
    0.46
     sauver
    0.46
    liv
    0.46
    Act Density 0.001%

    No Known Activations