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

    Neuronpedia

    INDEX
    Explanations

    programming elements or constructs related to variable assignments and function structures

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

    Token after equals sign

    np_acts-logits-general · gemini-2.0-flash

    return values from functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GTCX
    -0.66
     <<<<<<<<<<<<<<
    -0.60
     للمعارف
    -0.59
    SharedDtor
    -0.58
    PreferredItem
    -0.52
    lapsingToolbar
    -0.50
    migrationBuilder
    -0.50
    UserScript
    -0.47
     autorytatywna
    -0.46
    CppCodeGen
    -0.46
    POSITIVE LOGITS
     Verr
    0.38
     poh
    0.38
    pressed
    0.37
     Replaced
    0.35
     beaten
    0.35
    hidden
    0.33
     Opened
    0.33
    exposed
    0.32
     Menurut
    0.32
    depart
    0.31
    Act Density 0.125%

    No Known Activations