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

    Neuronpedia

    INDEX
    Explanations

    code blocks or formatted text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    秚
    0.46
    籶
    0.45
     мяг
    0.44
    Methylsulfanyl
    0.43
    楤
    0.41
    Businesses
    0.41
     verticales
    0.40
     φω
    0.40
     bersih
    0.40
    ссия
    0.40
    POSITIVE LOGITS
    it
    0.46
     slander
    0.43
    א
    0.41
     programmable
    0.41
     a
    0.39
    ̀
    0.39
     room
    0.39
     accuse
    0.38
    ה
    0.38
     artery
    0.38
    Act Density 0.002%

    No Known Activations