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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rede
    -0.08
     سبک
    -0.07
    طال
    -0.07
     тепер
    -0.07
    -stars
    -0.06
     sạn
    -0.06
    ți
    -0.06
    소년
    -0.06
     sagt
    -0.06
     Says
    -0.06
    POSITIVE LOGITS
    	loc
    0.07
     Prague
    0.07
    .Last
    0.06
    _RIGHT
    0.06
    +"</
    0.06
     것이
    0.06
     paras
    0.06
     middle
    0.06
     lineWidth
    0.06
     q
    0.06
    Act Density 0.004%

    No Known Activations