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

    Neuronpedia

    INDEX
    Explanations

    Expression of disbelief

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    му
    -0.07
    δη
    -0.06
    judul
    -0.06
     которая
    -0.06
    л
    -0.06
    яс
    -0.06
     Equals
    -0.06
    lý
    -0.06
     quasi
    -0.06
     이러
    -0.06
    POSITIVE LOGITS
    Weather
    0.07
     artificially
    0.07
    Routine
    0.06
     Rick
    0.06
    ीमत
    0.06
    Big
    0.06
    Miss
    0.06
    никам
    0.06
    datas
    0.06
     Inspiration
    0.06
    Act Density 0.014%

    No Known Activations