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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ЗА
    0.65
     হোয়াটসঅ্যাপ
    0.58
     irrespective
    0.55
    ându
    0.55
    اداسی
    0.55
    slideClass
    0.55
    ட்க
    0.54
     её
    0.53
     шла
    0.53
     Zá
    0.52
    POSITIVE LOGITS
     incrível
    0.72
    skyblue
    0.67
     newsc
    0.67
     popolo
    0.66
     storyteller
    0.65
     skyscraper
    0.64
    ೂರ್ಯ
    0.64
     pueblo
    0.63
     celebrity
    0.63
     Reporter
    0.63
    Act Density 0.001%

    No Known Activations