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

    Neuronpedia

    INDEX
    Explanations

    programming-related code structures and declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    true labeled with Delta

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.48
    nalités
    -0.45
     Sosten
    -0.44
    ,
    -0.44
     surla
    -0.43
     Schwert
    -0.43
     padat
    -0.42
     colspan
    -0.42
    (||
    -0.41
     otorg
    -0.41
    POSITIVE LOGITS
    expandindo
    0.54
     Taktlose
    0.52
     Italijani
    0.52
     Meksiku
    0.50
    المكان
    0.49
     nakalista
    0.48
    OGND
    0.48
    Tembelea
    0.47
     насељу
    0.46
    تفصیلات
    0.45
    Act Density 0.785%

    No Known Activations