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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    🥸
    1.40
    用来
    1.33
    দেখ
    1.29
     Andy
    1.28
    തിനുള്ള
    1.28
    Phenyl
    1.28
     saludar
    1.25
     Italiana
    1.25
     Physiol
    1.25
     Handwritten
    1.25
    POSITIVE LOGITS
    er
    1.23
    ö
    1.07
    or
    1.06
     होतो
    1.02
    ر
    1.01
    át
    0.99
    ра
    0.99
    ę
    0.97
    تو
    0.96
     ய
    0.96
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.