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

    Neuronpedia

    INDEX
    Explanations

    HOPE hotline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ك
    0.32
    btnUn
    0.31
     avec
    0.30
    ongono
    0.30
     juge
    0.30
    ustos
    0.30
     imprend
    0.29
    ürn
    0.29
     كنا
    0.29
    idalgo
    0.29
    POSITIVE LOGITS
    а
    0.37
    А
    0.31
    о
    0.29
    5
    0.28
    预览
    0.27
    Р
    0.27
    8
    0.27
    ’
    0.26
    З
    0.26
     Horizontal
    0.26
    Act Density 0.054%

    No Known Activations