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

    Neuronpedia

    INDEX
    Explanations

    still under development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    downs
    0.47
    Logout
    0.41
     downtime
    0.38
     downs
    0.38
     uts
    0.37
     logout
    0.37
     ಅನುಪ
    0.37
    ups
    0.36
    WHERE
    0.36
    起的
    0.36
    POSITIVE LOGITS
     out
    0.46
    צל
    0.45
     clown
    0.42
     профессии
    0.39
     Out
    0.37
     off
    0.37
    κέ
    0.37
    TintColor
    0.36
    туи
    0.36
     clowns
    0.35
    Act Density 0.037%

    No Known Activations