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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Zak
    0.43
     zak
    0.39
     ማ
    0.39
     Zak
    0.39
    क्र
    0.38
    oni
    0.38
     Mack
    0.38
     байгаа
    0.38
    irthday
    0.38
     eul
    0.36
    POSITIVE LOGITS
    acos
    0.44
    帐
    0.42
    account
    0.42
     Ports
    0.41
     మో
    0.40
    adamia
    0.40
    aron
    0.40
     Adam
    0.40
    adam
    0.39
     ADAM
    0.39
    Act Density 0.002%

    No Known Activations