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

    Neuronpedia

    INDEX
    Explanations

    notes with directional labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    --’
    0.40
     membaca
    0.38
     রাখার
    0.36
    ว่าจะ
    0.35
     OB
    0.35
     گاه
    0.35
    的概念
    0.35
    гем
    0.34
    💅
    0.34
     १६
    0.34
    POSITIVE LOGITS
    \[
    0.37
     সমর্থনে
    0.35
    una
    0.35
    aacute
    0.34
    Rew
    0.34
    ()?;
    0.34
     Recruiting
    0.34
     Hoff
    0.33
     partitioning
    0.33
    rarr
    0.32
    Act Density 0.001%

    No Known Activations