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

    Neuronpedia

    INDEX
    Explanations

    defining functions and classes in code

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

    Start of a function definition

    np_acts-logits-general · gemini-2.0-flash

    programming language function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     "
    -0.94
     "...
    -0.74
    ↵
    -0.73
     «
    -0.71
     '
    -0.71
     ;"
    -0.71
     [...]
    -0.71
     ;
    -0.70
     ";
    -0.70
     \"
    -0.67
    POSITIVE LOGITS
     CreateTagHelper
    0.92
     __
    0.80
    rungsseite
    0.73
     _
    0.63
     &___
    0.63
     بيها
    0.63
    &__
    0.63
    AsStream
    0.58
    adaptiveStyles
    0.57
    BeginContext
    0.56
    Act Density 0.052%

    No Known Activations