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

    Neuronpedia

    INDEX
    Explanations

    Definitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :↵↵
    -0.06
    爵
    -0.06
    ockets
    -0.06
    ┐
    -0.06
    ".↵
    -0.06
    、
    -0.06
    加入
    -0.06
     آنجا
    -0.06
    èles
    -0.06
    seudo
    -0.06
    POSITIVE LOGITS
     liste
    0.09
    _BUS
    0.07
    .iterator
    0.07
    _CUSTOM
    0.07
     enumerator
    0.06
    creative
    0.06
    وروب
    0.06
     comprar
    0.06
     pakistan
    0.06
    GED
    0.06
    Act Density 0.216%

    No Known Activations