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

    Neuronpedia

    INDEX
    Explanations

    scientific notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.65
     осигура
    0.63
    га
    0.61
    osi
    0.60
    ettes
    0.59
    liques
    0.59
    ي
    0.59
    ڑا
    0.59
    紾
    0.58
    is
    0.58
    POSITIVE LOGITS
     first
    0.57
     global
    0.56
     entire
    0.55
     two
    0.55
     ப
    0.55
     일이
    0.54
     northern
    0.54
    tow
    0.52
     recruiting
    0.52
     total
    0.52
    Act Density 0.006%

    No Known Activations