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

    Neuronpedia

    INDEX
    Explanations

    numerical values and formatting in a structured document

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

    numeric codes or identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atguigu
    -0.53
    jsonwebtoken
    -0.47
     bambú
    -0.47
     مرئيه
    -0.47
    zension
    -0.45
    NOPQRST
    -0.43
     TAMBIÉN
    -0.43
     contigo
    -0.42
     Notícias
    -0.42
    verifyException
    -0.41
    POSITIVE LOGITS
     kaarangay
    0.59
     Савезне
    0.54
     noDo
    0.48
    حياتها
    0.42
     indisponible
    0.41
    regular
    0.41
    medial
    0.40
     Italijanski
    0.40
    思わず
    0.40
    olino
    0.40
    Act Density 0.091%

    No Known Activations