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

    Neuronpedia

    INDEX
    Explanations

    Bitcoin and betting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    getPassword
    1.80
     rail
    1.76
     itibaren
    1.76
     আর্কাইভ
    1.75
     contend
    1.71
    $(".
    1.71
    𝑯
    1.69
     imposed
    1.67
     setback
    1.66
     flee
    1.65
    POSITIVE LOGITS
    z
    2.15
    н
    2.14
    न
    2.14
    n
    1.98
    ع
    1.94
    ⿷
    1.79
    ुत
    1.79
    د
    1.71
    蓣
    1.71
    ر
    1.60
    Act Density 0.081%

    No Known Activations