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

    Neuronpedia

    INDEX
    Explanations

    actions and information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cropland
    0.50
    Mogo
    0.45
    ному
    0.42
     ентите
    0.41
    க்கோ
    0.41
     contradicted
    0.40
    ंद
    0.39
    阻止
    0.39
     yattha
    0.39
    붉
    0.39
    POSITIVE LOGITS
     Atelier
    0.52
     other
    0.47
     Beginners
    0.46
     Crew
    0.46
     Young
    0.45
     @
    0.45
     Cyber
    0.45
     new
    0.44
     Year
    0.44
     Sistem
    0.44
    Act Density 0.008%

    No Known Activations