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

    Neuronpedia

    INDEX
    Explanations

    LLP

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .TabStop
    -0.07
    貉
    -0.07
    /color
    -0.07
    	light
    -0.07
    过分
    -0.07
    适度
    -0.06
    :".
    -0.06
    ().
    -0.06
     рем
    -0.06
    制止
    -0.06
    POSITIVE LOGITS
    ｃ
    0.07
     FactoryGirl
    0.07
     saturated
    0.07
    hões
    0.06
     trouvé
    0.06
    0.06
     whipping
    0.06
    ungalow
    0.06
    HF
    0.06
    <UFunction
    0.06
    Act Density 0.003%

    No Known Activations