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

    Neuronpedia

    INDEX
    Explanations

    improve outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ка
    0.52
    وتر
    0.48
    %>%
    0.46
    Фран
    0.46
    Му
    0.45
     kompos
    0.45
    ICAL
    0.44
    BOTH
    0.44
     distill
    0.43
    Ⅽ
    0.42
    POSITIVE LOGITS
    confirm
    0.46
    ј
    0.46
     notifying
    0.44
     ট
    0.44
     इनकार
    0.44
    nél
    0.43
     поез
    0.42
     Такой
    0.42
     Confirm
    0.42
    lng
    0.41
    Act Density 0.002%

    No Known Activations