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

    Neuronpedia

    INDEX
    Explanations

    setting values or properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ರಚ
    0.47
     organisé
    0.39
     neler
    0.38
    ையைக்
    0.38
    تاح
    0.37
     боро
    0.37
     خلق
    0.36
    ეგ
    0.36
     courbe
    0.36
    ртка
    0.36
    POSITIVE LOGITS
     setting
    1.40
     设置
    1.38
    设置
    1.35
     Setting
    1.35
    を設定
    1.30
     setter
    1.29
    Setting
    1.28
     set
    1.27
    setting
    1.27
     setzen
    1.26
    Act Density 0.035%

    No Known Activations