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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :System
    -0.07
     と
    -0.07
    _require
    -0.07
    極
    -0.07
     이상
    -0.07
    iss
    -0.07
     či
    -0.07
    _HDR
    -0.07
     mills
    -0.07
     덤프
    -0.06
    POSITIVE LOGITS
    matplotlib
    0.06
    екси
    0.06
    Amt
    0.06
     детей
    0.06
    !!!!!
    0.06
    ودة
    0.06
     nunca
    0.06
    entered
    0.05
    etxt
    0.05
     viper
    0.05
    Act Density 0.025%

    No Known Activations