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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     způ
    0.45
    zelfde
    0.45
     smach
    0.45
     পারেনা
    0.44
    etse
    0.44
     meestal
    0.44
    تا
    0.43
     ईमित्र
    0.43
    𒅎
    0.43
    伒
    0.43
    POSITIVE LOGITS
    A
    0.52
    H
    0.50
    ຜ
    0.48
    B
    0.48
    R
    0.48
    D
    0.47
    с
    0.46
     усили
    0.46
    F
    0.46
    T
    0.44
    Act Density 0.000%

    No Known Activations