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

    Neuronpedia

    INDEX
    Explanations

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ks
    0.63
    atan
    0.61
    y
    0.56
    inal
    0.54
     instead
    0.52
     mentioned
    0.50
    ated
    0.50
     stem
    0.50
    den
    0.48
    -
    0.48
    POSITIVE LOGITS
     વધુ
    0.85
     обновление
    0.84
     आंकड़ा
    0.81
    SelectList
    0.80
     снижение
    0.78
     certificación
    0.76
     المزيد
    0.75
     είχε
    0.73
     количество
    0.73
    UTRON
    0.73
    Act Density 0.459%

    No Known Activations