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

    Neuronpedia

    INDEX
    Explanations

    references to helper functions in code or documentation

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

    programming helper components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.73
     Infórmanos
    -0.65
    hoeddwyd
    -0.58
     propOrder
    -0.57
     Paglinawan
    -0.57
     OMITBAD
    -0.56
    rungsseite
    -0.56
     autorytatywna
    -0.54
     ویکی‌پدی
    -0.52
    SharedDtor
    -0.51
    POSITIVE LOGITS
     helper
    0.67
     utilities
    0.59
     Helper
    0.56
     tools
    0.55
     utility
    0.53
     tool
    0.52
     classes
    0.50
     functions
    0.48
    helper
    0.48
     Hilfs
    0.45
    Act Density 0.010%

    No Known Activations