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

    Neuronpedia

    INDEX
    Explanations

    non-english words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Magist
    0.48
    有個
    0.46
     parten
    0.45
     resear
    0.45
    $[
    0.42
     Projekt
    0.41
     automat
    0.40
     Faktoren
    0.40
    眥
    0.40
     TECH
    0.40
    POSITIVE LOGITS
    filled
    0.43
    îtes
    0.41
     основном
    0.41
    asher
    0.41
     llena
    0.41
     живот
    0.41
    シェア
    0.41
     нижней
    0.41
     ನೀ
    0.41
    қи
    0.41
    Act Density 0.004%

    No Known Activations