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

    Neuronpedia

    INDEX
    Explanations

    i'm learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     twee
    0.37
     thwart
    0.36
    聲
    0.36
     플레이
    0.35
     Dismiss
    0.34
    ?
    0.34
     can
    0.34
     manages
    0.34
     SoundCloud
    0.33
    Ok
    0.33
    POSITIVE LOGITS
    ﺡ
    0.40
    ColumnHeaders
    0.36
     περισσότε
    0.36
     partito
    0.35
    arbeit
    0.35
    ுறு
    0.34
    揆
    0.33
    իմ
    0.33
    ܚ
    0.33
    expédition
    0.32
    Act Density 0.014%

    No Known Activations