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

    Neuronpedia

    INDEX
    Explanations

    voltage and potential difference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ס
    0.51
    ام
    0.48
    ג
    0.45
    ש
    0.44
     pedest
    0.44
     tersangka
    0.44
    סטי
    0.42
     osl
    0.42
     ridurre
    0.41
    ൂ
    0.41
    POSITIVE LOGITS
    握
    0.48
     النف
    0.47
    独立
    0.47
    unsafe
    0.46
     تكون
    0.45
    нат
    0.45
    MW
    0.45
    已经
    0.43
    Independent
    0.43
    控件
    0.43
    Act Density 0.000%

    No Known Activations