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

    Neuronpedia

    INDEX
    Explanations

    physical or state changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ನೀವು
    0.42
    いただいた
    0.42
    それに
    0.41
     Inspirational
    0.41
    那样
    0.40
    egos
    0.40
     इसका
    0.40
     நீங்கள்
    0.39
    amir
    0.38
     получите
    0.38
    POSITIVE LOGITS
     happens
    0.70
     inilah
    0.61
     azonban
    0.59
     however
    0.59
     happened
    0.57
     avviene
    0.56
     translates
    0.55
     wiederum
    0.54
     culminates
    0.54
     occurs
    0.53
    Act Density 0.024%

    No Known Activations