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

    Neuronpedia

    INDEX
    Explanations

    json structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Acetic
    0.46
     climbed
    0.44
    Rising
    0.44
     Climbing
    0.44
     proteolytic
    0.43
     झरने
    0.41
    لسل
    0.41
     Pferde
    0.41
    Cardiac
    0.41
     climbs
    0.40
    POSITIVE LOGITS
     {"
    0.80
     [{"
    0.77
     "
    0.75
    {"
    0.75
     `"
    0.74
     ["
    0.71
     json
    0.70
    ":{"
    0.68
    ={"
    0.68
    ({"
    0.67
    Act Density 0.094%

    No Known Activations