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

    Neuronpedia

    INDEX
    Explanations

    hexadecimal strings and addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     copi
    0.69
    jenigen
    0.68
    цах
    0.66
     t
    0.64
     stuffs
    0.63
     kuhusu
    0.61
     unrelenting
    0.61
     naan
    0.61
     l
    0.60
     caloric
    0.60
    POSITIVE LOGITS
    ao
    0.64
    something
    0.64
     Пока
    0.64
     >=
    0.63
     หลังจาก
    0.63
    ;
    0.63
     –
    0.61
     =>
    0.59
    storey
    0.58
    aea
    0.57
    Act Density 0.013%

    No Known Activations