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

    Neuronpedia

    INDEX
    Explanations

    method definitions in programming code

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

    setting method names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    splan
    -0.39
    forRoot
    -0.37
    饶
    -0.34
     concor
    -0.34
    ABC
    -0.33
     along
    -0.33
    abab
    -0.32
    sche
    -0.32
    herzog
    -0.32
    fpath
    -0.32
    POSITIVE LOGITS
     snippetHide
    0.84
     set
    0.82
    set
    0.68
    WriteBarrier
    0.65
    帖最后由
    0.59
    Autoritní
    0.58
     propOrder
    0.58
    BeginContext
    0.55
    AddHtmlAttribute
    0.54
    SharedDtor
    0.54
    Act Density 0.004%

    No Known Activations