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

    Neuronpedia

    INDEX
    Explanations

    references to instance variables and method arguments in a programming context

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

    Code snippets using "self"

    np_acts-logits-general · gemini-2.0-flash

    object-oriented programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.55
     utafitiHapana
    -0.51
    AndEndTag
    -0.50
    indd
    -0.48
    جمعیت
    -0.47
     fieldNum
    -0.47
    ümüş
    -0.46
    KommentareTeilen
    -0.46
    Traducción
    -0.46
    HasBeenSet
    -0.45
    POSITIVE LOGITS
     للاسماء
    0.58
    paravant
    0.56
    ,*
    0.54
    twimg
    0.53
    ;*
    0.50
    `;
    0.48
    TabIndex
    0.48
    ;</
    0.48
     กรัม
    0.48
    self
    0.48
    Act Density 0.096%

    No Known Activations