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

    Neuronpedia

    INDEX
    Explanations

    programming language syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    isce
    0.45
    enar
    0.43
     unveiled
    0.42
    inu
    0.42
    кия
    0.42
    ა
    0.42
     diverted
    0.42
    ਾ
    0.41
    িক
    0.41
    گي
    0.41
    POSITIVE LOGITS
     It
    0.56
     مج
    0.48
     पाठक
    0.47
     cardiology
    0.47
    Folders
    0.45
    Found
    0.45
    Readers
    0.45
    Headline
    0.45
     урока
    0.43
    Lect
    0.43
    Act Density 0.001%

    No Known Activations