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

    Neuronpedia

    INDEX
    Explanations

    iostream library inclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hist
    0.46
     ಸ್ಥಾನ
    0.41
    Wert
    0.40
    Hist
    0.39
     வடிவ
    0.38
    ക്കിയത്
    0.38
     الواحده
    0.38
     Hist
    0.38
    face
    0.37
     ውስ
    0.37
    POSITIVE LOGITS
     package
    0.77
     pacote
    0.65
    包
    0.64
     пакет
    0.63
     paquete
    0.60
    软件包
    0.60
     paket
    0.58
     module
    0.57
    package
    0.57
    パッケージ
    0.55
    Act Density 0.003%

    No Known Activations