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

    Neuronpedia

    INDEX
    Explanations

    advertising

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    1.16
    Throttle
    1.06
    ১
    0.88
    ឋ
    0.87
    am
    0.86
     whistling
    0.78
    0.78
    <0x0D>
    0.78
     τ
    0.77
    usepackage
    0.77
    POSITIVE LOGITS
     расходов
    1.10
    س
    1.01
     valorem
    0.96
    म
    0.93
    广告
    0.93
     hoard
    0.93
     loadImage
    0.93
     advertising
    0.91
     hoarding
    0.89
    広告
    0.88
    Act Density 0.064%

    No Known Activations