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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ה
    1.37
    inkan
    1.28
    相反
    1.17
     tetap
    1.13
     Frozen
    1.12
    seg
    1.12
    Mutual
    1.04
    Frozen
    1.02
    嚟
    1.01
    もの
    1.00
    POSITIVE LOGITS
    RH
    1.29
     affectionate
    1.28
     outbursts
    1.26
     pratis
    1.25
     perde
    1.23
     autonomía
    1.23
    holders
    1.22
     seguirá
    1.22
     heifers
    1.20
     netizens
    1.19
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.