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

    Neuronpedia

    INDEX
    Explanations

    code syntax or structured text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ير
    0.96
    يا
    0.86
     Describes
    0.83
    ارك
    0.80
     sulfon
    0.80
     alkaloids
    0.77
    动物
    0.77
    काल
    0.75
     migliorare
    0.75
     décider
    0.75
    POSITIVE LOGITS
     поскольку
    0.97
    <0x80>
    0.91
    $
    0.85
    {
    0.80
    +
    0.77
    (
    0.73
     बजकर
    0.73
     पाली
    0.69
    lovens
    0.67
     спустя
    0.67
    Act Density 0.001%

    No Known Activations