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

    Neuronpedia

    INDEX
    Explanations

    ________

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ạ
    -0.08
    罕见
    -0.07
     synagogue
    -0.07
    /el
    -0.07
    不是一个
    -0.07
    _constructor
    -0.07
    bió
    -0.07
     affiliated
    -0.07
     flair
    -0.07
    还是很
    -0.06
    POSITIVE LOGITS
    醒来
    0.07
     Extra
    0.07
    悭
    0.07
    (tokens
    0.07
    .text
    0.06
     Focus
    0.06
    _accessor
    0.06
    stop
    0.06
    .test
    0.06
    ('#
    0.06
    Act Density 0.003%

    No Known Activations