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

    Neuronpedia

    INDEX
    Explanations

    Acronyms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Note
    -0.07
     vex
    -0.07
     communauté
    -0.07
     Paginator
    -0.06
    itä
    -0.06
    reshape
    -0.06
    ília
    -0.06
    liğe
    -0.06
    ﮮ
    -0.06
    自主创新
    -0.06
    POSITIVE LOGITS
     EVENT
    0.07
     Burger
    0.07
     ";
↵
    0.07
     SERIAL
    0.07
    (FILE
    0.06
     BUF
    0.06
    发生在
    0.06
    Permanent
    0.06
    _FAILURE
    0.06
     мощ
    0.06
    Act Density 0.101%

    No Known Activations