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

    Neuronpedia

    INDEX
    Explanations

    modelmodel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Depends
    0.73
     cropped
    0.66
     cabs
    0.64
     ARE
    0.63
     Originally
    0.63
     depend
    0.63
     depending
    0.62
     factions
    0.61
     dependent
    0.61
     DEPEND
    0.61
    POSITIVE LOGITS
    <end_of_turn>
    0.92
    íss
    0.68
    Ꭻ
    0.68
    ه‌ها
    0.67
    égio
    0.65
     exposición
    0.65
     escolas
    0.64
    enció
    0.64
    ână
    0.63
    ósito
    0.63
    Act Density 0.295%

    No Known Activations