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

    Neuronpedia

    INDEX
    Explanations

    asking for information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IT
    0.97
    ين
    0.95
    ιάς
    0.94
    тация
    0.92
    आ
    0.92
    ై
    0.92
    금
    0.91
    ر
    0.90
     انب
    0.89
    ین
    0.88
    POSITIVE LOGITS
    ക്ഷണ
    1.08
     conquist
    1.02
     criterio
    1.01
     asuntos
    1.01
    ght
    0.98
     invoking
    0.96
     advocating
    0.95
    :**
    0.95
     acerca
    0.94
     advocacy
    0.94
    Act Density 0.045%

    No Known Activations