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

    Neuronpedia

    INDEX
    Explanations

    integer declarations and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    en
    1.17
    in
    1.00
    रन
    0.93
     meditative
    0.92
     साजरा
    0.84
    ه
    0.83
    ாட்டு
    0.82
    of
    0.81
    o
    0.81
    lst
    0.79
    POSITIVE LOGITS
    പ്പെടുത്തി
    0.90
     autore
    0.88
     Winchester
    0.86
     Pole
    0.86
    issime
    0.86
    ;
    0.81
     Salts
    0.81
    ኛውም
    0.80
     Shelf
    0.79
     currentIndex
    0.79
    Act Density 0.055%

    No Known Activations