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

    Neuronpedia

    INDEX
    Explanations

    let's break down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ות
    1.56
    наче
    1.47
    능
    1.40
    ותו
    1.23
     silly
    1.19
     суще
    1.19
    alyse
    1.16
    lardan
    1.16
    lasting
    1.15
    ed
    1.14
    POSITIVE LOGITS
    িয়ান
    1.58
     LinearLayout
    1.48
     zirconia
    1.42
    ̽
    1.41
     renseign
    1.38
    {~
    1.37
     Př
    1.37
    ☒
    1.33
     thirds
    1.33
    купки
    1.32
    Act Density 0.124%

    No Known Activations