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

    Neuronpedia

    INDEX
    Explanations

    writing genres and styles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🚄
    0.49
     খুঁজ
    0.47
     न्यायिक
    0.44
    耶稣
    0.44
    铁路
    0.43
     খুঁজে
    0.43
    鬪
    0.42
     الاطلاع
    0.40
     পণ্য
    0.40
     ड्यू
    0.39
    POSITIVE LOGITS
    E
    0.50
    M
    0.46
    Ghost
    0.44
     Schreib
    0.44
     fil
    0.44
     writing
    0.44
    d
    0.43
     Un
    0.42
    стики
    0.42
     resume
    0.41
    Act Density 0.000%

    No Known Activations