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

    Neuronpedia

    INDEX
    Explanations

    refuse politely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ចាយ
    0.53
    ן
    0.52
     Цена
    0.47
     bouncing
    0.46
     contesting
    0.45
    ড়িত
    0.45
    tements
    0.45
    m
    0.45
     మ
    0.44
     handlebars
    0.44
    POSITIVE LOGITS
    ocytosis
    0.54
    iging
    0.53
    Of
    0.52
    '
    0.49
    App
    0.49
    Although
    0.49
     asp
    0.48
    Asp
    0.48
    ellen
    0.46
    (
    0.46
    Act Density 0.001%

    No Known Activations