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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    asting
    0.47
     subject
    0.44
    nomina
    0.43
     caregiver
    0.43
     deposito
    0.42
    ttino
    0.42
    беріга
    0.42
    翁
    0.42
    ーム
    0.41
     wholesome
    0.41
    POSITIVE LOGITS
    h
    0.48
     Shopping
    0.45
    Policy
    0.43
    හ
    0.40
    ar
    0.40
    H
    0.40
    Shopping
    0.40
     Hobby
    0.40
     代表
    0.39
     Policy
    0.39
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.