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

    Neuronpedia

    INDEX
    Explanations

    instances of the words "das", "de", "uma", "única", "suas", "as", "espor", "la", "las", and "llenar".

    oai_token-act-pair · gemini-2.0-flash

    non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AnimationsModule
    -0.65
     nahilalakip
    -0.60
    Бележки
    -0.58
     internetowa
    -0.58
     שוליים
    -0.57
    SequentialGroup
    -0.56
     invokingState
    -0.54
     referenties
    -0.54
    //
    -0.53
    SpringRunner
    -0.53
    POSITIVE LOGITS
     marquées
    0.52
    reas
    0.45
    Elles
    0.44
     Lives
    0.44
     Приступљено
    0.43
     esas
    0.43
    Trades
    0.42
     Clow
    0.41
    عاية
    0.40
    xas
    0.40
    Act Density 0.143%

    No Known Activations