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

    Neuronpedia

    INDEX
    Explanations

    programming language keywords and functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ॒
    0.44
     н
    0.41
    ॑
    0.41
    ล์
    0.38
    िय
    0.38
    प
    0.38
    階段
    0.37
    ฺ
    0.37
    ่น
    0.36
    тні
    0.36
    POSITIVE LOGITS
     useNavigate
    0.45
     cursus
    0.40
     NotImplemented
    0.39
    opardy
    0.39
    !`
    0.39
     traduire
    0.38
     HttpServer
    0.38
     Tradu
    0.38
     &&
    0.38
     negativa
    0.37
    Act Density 0.025%

    No Known Activations