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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by other numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     assists
    0.54
    assist
    0.48
     Assists
    0.47
     assist
    0.47
     Assist
    0.46
    助
    0.46
     assisting
    0.46
    Assist
    0.45
    Hudson
    0.41
     assistive
    0.40
    POSITIVE LOGITS
     seven
    0.55
     siete
    0.45
     ocho
    0.43
     eight
    0.42
     النهائي
    0.41
     terre
    0.41
     nine
    0.40
     otto
    0.40
     Uncle
    0.40
     seis
    0.39
    Act Density 0.077%

    No Known Activations