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

    Neuronpedia

    INDEX
    Explanations

    programming language function definitions and formatting instructions

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

    editor-fold comments and code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cuenca
    -0.45
     industriales
    -0.41
     cárcel
    -0.39
     camiones
    -0.39
     fleuve
    -0.38
     fidé
    -0.37
     crossorigin
    -0.36
     nobre
    -0.36
     drapeau
    -0.36
     batalla
    -0.35
    POSITIVE LOGITS
    WithFormat
    1.09
     Савезне
    0.89
     للاسماء
    0.75
    parsedMessage
    0.73
     ویکی‌پدی
    0.71
    bootstrapcdn
    0.68
     OMITBAD
    0.67
     saites
    0.65
    __":
    0.64
    StoryboardSegue
    0.64
    Act Density 0.001%

    No Known Activations