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

    Neuronpedia

    INDEX
    Explanations

    comparison

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    thresh
    -0.07
    _de
    -0.07
     вели
    -0.06
     indir
    -0.06
     استرات
    -0.06
     acet
    -0.06
    .sig
    -0.06
     یاد
    -0.06
    щин
    -0.06
     рабо
    -0.06
    POSITIVE LOGITS
     můžeme
    0.07
    .master
    0.07
     boarding
    0.07
     needing
    0.07
    Comparison
    0.07
    $xml
    0.07
    องท
    0.06
     Comparison
    0.06
    structures
    0.06
    Pixels
    0.06
    Act Density 0.002%

    No Known Activations