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

    Neuronpedia

    INDEX
    Explanations

    books, magnification, offenses, Python

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     parecía
    0.48
    MORDOR
    0.48
     étro
    0.47
     করেছিলেন
    0.46
    ăpadă
    0.46
     města
    0.45
    ómago
    0.45
    роятно
    0.44
    𝖆
    0.44
     शहरा
    0.44
    POSITIVE LOGITS
    /
    0.71
    ,
    0.64
    、
    0.63
     \
    0.62
    \
    0.61
     /
    0.59
     (
    0.57
    ，
    0.54
     and
    0.54
     &
    0.52
    Act Density 0.002%

    No Known Activations