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

    Neuronpedia

    INDEX
    Explanations

    code, file formats

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nameLabel
    -0.07
     insanlar
    -0.07
    dur
    -0.07
    .keySet
    -0.07
    .AsyncTask
    -0.07
    _backend
    -0.07
     陈
    -0.07
     назва
    -0.07
    ==-
    -0.06
    ylinder
    -0.06
    POSITIVE LOGITS
    ,''
    0.06
    sigmoid
    0.06
     '');↵
    0.06
     Wikip
    0.06
    طة
    0.06
     juven
    0.06
     forcibly
    0.06
     tường
    0.06
    ियम
    0.06
    рю
    0.06
    Act Density 0.025%

    No Known Activations