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

    Neuronpedia

    INDEX
    Explanations

    code and programming

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WebServlet
    0.82
    জ্
    0.77
    ouvement
    0.70
     му
    0.68
    Mush
    0.67
    ಿವ
    0.67
     चक्रवृद्धि
    0.66
     実
    0.65
    ňuje
    0.65
     ー
    0.65
    POSITIVE LOGITS
     форма
    0.71
     ตั้ง
    0.68
     broker
    0.63
    formal
    0.63
     Broker
    0.61
     gestellt
    0.61
    బ్బ
    0.59
     Formal
    0.58
    astica
    0.58
     Inj
    0.58
    Act Density 0.008%

    No Known Activations