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

    Neuronpedia

    INDEX
    Explanations

    during specific periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prizes
    0.45
     модель
    0.44
    คุณภาพ
    0.44
     അടിസ്ഥാന
    0.44
    ოტ
    0.43
     имеет
    0.43
    সাথে
    0.42
    ற்கான
    0.42
     эффек
    0.42
     感じ
    0.42
    POSITIVE LOGITS
    during
    0.91
     during
    0.91
     During
    0.89
     दौरान
    0.83
    期間
    0.82
    During
    0.81
    期间
    0.80
     durante
    0.80
     período
    0.76
     أثناء
    0.75
    Act Density 0.060%

    No Known Activations