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

    Neuronpedia

    INDEX
    Explanations

    sequences of punctuation marks or special characters

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

    special characters and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.79
    évaluateur
    -0.74
    MLLoader
    -0.73
     Monfieur
    -0.68
     للاسماء
    -0.67
    WriteTagHelper
    -0.65
    CloseOperation
    -0.64
    ########.
    -0.62
    AndEndTag
    -0.59
     chofe
    -0.59
    POSITIVE LOGITS
    (:,:,
    0.46
    3
    0.45
     =
    0.45
     &&
    0.44
     Grü
    0.42
     III
    0.42
     (
    0.40
     üçün
    0.38
     rank
    0.38
     Third
    0.38
    Act Density 0.050%

    No Known Activations