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

    Neuronpedia

    INDEX
    Explanations

    zotero

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Porque
    0.65
    Assim
    0.62
    и
    0.61
    ுங்கள்
    0.61
    Pu
    0.60
    그러
    0.60
    их
    0.60
    Pero
    0.59
    ิล
    0.58
    亙
    0.58
    POSITIVE LOGITS
    ximity
    0.70
     boyfriend
    0.64
    ра
    0.63
    рка
    0.62
     recombination
    0.60
     deposition
    0.60
     طریقے
    0.60
     trwa
    0.59
     arrhythmias
    0.58
     temu
    0.57
    Act Density 0.001%

    No Known Activations