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

    Neuronpedia

    INDEX
    Explanations

    find

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    useppe
    -0.07
     argparse
    -0.07
    供热
    -0.07
     الوطن
    -0.07
     RTE
    -0.07
    巾
    -0.06
    奶粉
    -0.06
    ۊ
    -0.06
     Report
    -0.06
    💋
    -0.06
    POSITIVE LOGITS
    勾
    0.07
    Endpoint
    0.07
    端
    0.07
    ­i
    0.07
     instantiated
    0.07
     medi
    0.06
     calorie
    0.06
     scrollbar
    0.06
     specializes
    0.06
    _ARGS
    0.06
    Act Density 0.050%

    No Known Activations