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

    Neuronpedia

    INDEX
    Explanations

    maintainability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝒆
    2.93
    𝒓
    2.84
    מ
    2.82
    ிகள்
    2.66
     hatched
    2.60
    𝒔
    2.55
    ﹝
    2.50
     mAbs
    2.50
    стям
    2.37
    па
    2.35
    POSITIVE LOGITS
    ering
    3.33
    ン
    2.97
    ered
    2.96
    ه
    2.91
     certeza
    2.87
    eringen
    2.85
     цело
    2.84
    ে
    2.83
    tı
    2.77
    े
    2.75
    Act Density 0.048%

    No Known Activations