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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     unwittingly
    0.44
    ਵਾ
    0.43
    aktoren
    0.42
     цвета
    0.42
     अजून
    0.41
    ENDED
    0.40
     indigo
    0.39
     unintentionally
    0.39
     Minimalism
    0.39
    を開始
    0.39
    POSITIVE LOGITS
    s
    0.54
    avacanam
    0.51
    ς
    0.51
     عہد
    0.50
     toz
    0.50
     président
    0.47
    ład
    0.46
     Srps
    0.46
     rę
    0.46
     presidente
    0.46
    Act Density 0.001%

    No Known Activations