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

    Neuronpedia

    INDEX
    Explanations

    code blocks and special characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rams
    0.70
    Bingo
    0.65
    炤
    0.65
    Кон
    0.64
     suitcase
    0.63
    0.62
    VIC
    0.60
    0.60
     Wilton
    0.59
     VIC
    0.59
    POSITIVE LOGITS
    >>&
    0.67
     unterwegs
    0.67
     Appeal
    0.66
     eigenfunctions
    0.66
    urow
    0.65
     কর্মরত
    0.65
    ப்போது
    0.64
    пла
    0.62
     lad
    0.61
     mengak
    0.61
    Act Density 0.142%

    No Known Activations