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

    Neuronpedia

    INDEX
    Explanations

    parts of sorts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ح
    2.41
    ২০
    2.09
    Eau
    2.03
    buf
    1.95
    sthe
    1.94
    その
    1.91
    €™
    1.90
    ()=>{
    1.89
    ज
    1.88
     salvation
    1.86
    POSITIVE LOGITS
     sorts
    2.11
     видов
    1.98
    Всем
    1.85
     selves
    1.82
     harms
    1.80
    tei
    1.79
     הן
    1.79
    eseen
    1.79
     kinds
    1.78
     phận
    1.73
    Act Density 0.090%

    No Known Activations