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

    Neuronpedia

    INDEX
    Explanations

    nothingness in multiple languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     colère
    0.36
    𝓰
    0.34
     تجزی
    0.34
     znacznie
    0.33
     মহাপ
    0.33
     Both
    0.33
     ゙
    0.33
    阀
    0.33
     افر
    0.33
    🐠
    0.33
    POSITIVE LOGITS
    ไม่มี
    0.95
    没有任何
    0.93
     nenhuma
    0.92
     keine
    0.91
     nenhum
    0.91
     ninguna
    0.89
     geen
    0.88
    没有什么
    0.88
     없음
    0.88
     nothing
    0.88
    Act Density 0.496%

    No Known Activations