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

    Neuronpedia

    INDEX
    Explanations

    entities and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    хо
    0.49
     Quis
    0.49
     ಪ್ರಯತ್ನ
    0.48
     Гра
    0.47
    мас
    0.47
     Quiz
    0.47
    Ꮣ
    0.46
    ıll
    0.46
     Пло
    0.46
     Minist
    0.46
    POSITIVE LOGITS
    soil
    0.52
    يين
    0.48
     नीति
    0.48
    fails
    0.47
    ี้
    0.47
    /(
    0.47
     håll
    0.47
    IVITY
    0.46
    tsi
    0.46
    쵝
    0.46
    Act Density 0.000%

    No Known Activations