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

    Neuronpedia

    INDEX
    Explanations

    title in AppBar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enclosures
    0.38
     ostat
    0.37
     cotton
    0.37
    ansch
    0.37
     zeros
    0.36
     lunches
    0.35
     coton
    0.35
     cuisses
    0.35
    underwear
    0.35
     fractions
    0.35
    POSITIVE LOGITS
     title
    1.17
    setTitle
    1.17
     título
    1.11
     제목
    1.11
    Title
    1.04
    タイトル
    1.04
    标题
    1.03
    title
    1.02
     Titel
    1.02
     titulo
    1.00
    Act Density 0.006%

    No Known Activations