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

    Neuronpedia

    INDEX
    Explanations

    avoidance algorithms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     напи
    0.42
     ಹೆಸ
    0.41
     современного
    0.39
    Duong
    0.38
     ኢ
    0.38
    ల్
    0.38
     ભાવ
    0.38
     नेशनल
    0.37
     класси
    0.37
     produktu
    0.37
    POSITIVE LOGITS
     asla
    0.39
     ReLU
    0.37
    쥐
    0.37
    emails
    0.37
    হয়
    0.35
    }`}
    0.35
     activation
    0.35
    ="";
    0.34
    睡眠
    0.33
     Hemsworth
    0.33
    Act Density 0.000%

    No Known Activations