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

    Neuronpedia

    INDEX
    Explanations

    stackpath

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _shop
    -0.06
    电
    -0.06
     piano
    -0.06
     fh
    -0.06
     Supplements
    -0.06
    '$
    -0.06
    	ap
    -0.06
    odule
    -0.06
    発表
    -0.06
     bump
    -0.06
    POSITIVE LOGITS
    оки
    0.07
    τογραφ
    0.07
    lood
    0.06
    .twimg
    0.06
    >↵
    0.06
    .out
    0.06
     responding
    0.06
    TEGER
    0.06
     Hij
    0.06
    Column
    0.06
    Act Density 0.000%

    No Known Activations