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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     html
    1.15
    html
    1.12
    Html
    1.02
     Html
    1.02
     HTML
    0.97
    HTML
    0.87
    ku
    0.69
    ScriptBuf
    0.68
    Script
    0.67
    htm
    0.66
    POSITIVE LOGITS
     ativo
    0.76
     actives
    0.72
    镗
    0.71
    stem
    0.69
     attend
    0.69
     수도
    0.67
    ንድ
    0.67
     بينهم
    0.67
    rend
    0.67
     restore
    0.67
    Act Density 0.004%

    No Known Activations