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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ando
    0.62
    اتی
    0.60
    ła
    0.58
    ана
    0.57
     فی
    0.57
    ala
    0.57
     transición
    0.57
     curated
    0.56
    acterísticas
    0.56
     melodic
    0.55
    POSITIVE LOGITS
    said
    0.50
    _
    0.47
    ↵
    0.45
     Herrn
    0.45
     اوقات
    0.45
    ឪ
    0.45
    Polit
    0.45
    ితీ
    0.44
     Herzen
    0.44
     Instinct
    0.44
    Act Density 0.254%

    No Known Activations