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

    Neuronpedia

    INDEX
    Explanations

    list item markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﾄ
    0.32
    ুতরাং
    0.32
    ঠা
    0.31
    飧
    0.31
    톄
    0.31
     这是
    0.30
     operands
    0.30
    UseVisualStyle
    0.29
    रीन
    0.29
     দ্য
    0.29
    POSITIVE LOGITS
    <ul>
    0.91
    •
    0.91
    0.90
    *
    0.89
     •
    0.83
    ①
    0.81
    0.79
    ●
    0.79
     ・
    0.77
     ●
    0.75
    Act Density 0.125%

    No Known Activations