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

    Neuronpedia

    INDEX
    Explanations

    lists of components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ，
    0.43
     simplification
    0.41
    SpriteCollision
    0.40
     착
    0.39
    ッグ
    0.39
     coloration
    0.38
     epitaxial
    0.37
    ссор
    0.37
     liberalization
    0.37
     erreur
    0.37
    POSITIVE LOGITS
     hoặc
    0.46
     Saleh
    0.45
     அல்லது
    0.45
     veya
    0.44
    ütfen
    0.43
     Ladakh
    0.43
    🚮
    0.43
     অথবা
    0.42
     Bož
    0.42
     અથવા
    0.42
    Act Density 0.006%

    No Known Activations