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

    Neuronpedia

    INDEX
    Explanations

    descriptions of complexity and state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     são
    0.44
     è
    0.41
     Studies
    0.41
     incessantly
    0.40
    0.40
     stále
    0.39
     dominates
    0.39
     sempre
    0.39
     তথা
    0.38
     studies
    0.38
    POSITIVE LOGITS
    可以让
    0.39
    xcuser
    0.34
    eredReader
    0.34
     लोकांना
    0.34
    🌸
    0.34
    takePhotoButton
    0.33
    随便
    0.33
    arankan
    0.33
    会让
    0.33
    cknow
    0.33
    Act Density 0.093%

    No Known Activations