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

    Neuronpedia

    INDEX
    Explanations

    list item markers and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ग
    0.47
    ਟੀ
    0.46
     specialising
    0.45
     especializado
    0.45
     modernos
    0.45
    帶來
    0.44
     dynasties
    0.44
     empires
    0.44
    聳
    0.43
     राजांनी
    0.43
    POSITIVE LOGITS
     unpublished
    0.59
     Notebook
    0.59
     autobi
    0.59
    Fragment
    0.57
     Suite
    0.56
     fragment
    0.54
     fragments
    0.54
     notebook
    0.54
     Fragment
    0.54
     self
    0.52
    Act Density 0.221%

    No Known Activations