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

    Neuronpedia

    INDEX
    Explanations

    rich history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     دول
    0.59
     بجلی
    0.57
    Fle
    0.54
     molécules
    0.54
     electricidad
    0.52
     मिश्रण
    0.51
     смесь
    0.51
     eaters
    0.48
     mía
    0.48
     dosta
    0.47
    POSITIVE LOGITS
    ä
    0.65
     Storia
    0.62
    ਣ
    0.62
    ieft
    0.60
    issão
    0.57
    ו
    0.57
     it
    0.56
    vn
    0.55
    ｧ
    0.55
    history
    0.55
    Act Density 0.002%

    No Known Activations