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

    Neuronpedia

    INDEX
    Explanations

    just testing/saying/checking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    craft
    1.51
    তীশ
    1.49
    ORITY
    1.45
    ôm
    1.38
     majoring
    1.38
    righteous
    1.37
    pathetic
    1.37
    dataframe
    1.33
    סה
    1.33
    ினார்கள்
    1.32
    POSITIVE LOGITS
    ১
    1.73
     ರಲ್ಲಿ
    1.67
    Что
    1.66
     Въ
    1.65
    сь
    1.56
    ০
    1.55
     Puede
    1.54
     која
    1.53
    ための
    1.51
     campaña
    1.51
    Act Density 0.001%

    No Known Activations