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

    Neuronpedia

    INDEX
    Explanations

    code-related terms or functions used in programming

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

    programming language constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.61
    aarrggbb
    -0.59
     Италијани
    -0.52
     OMITBAD
    -0.50
    NameInMap
    -0.49
     ujednoznacz
    -0.46
    ፩
    -0.44
     Administrativna
    -0.41
    AISSEE
    -0.41
     autorytatywna
    -0.40
    POSITIVE LOGITS
     very
    0.53
     plumes
    0.49
    urts
    0.48
    Fü
    0.48
    iglio
    0.46
    accus
    0.45
    󠁬
    0.45
     knuckles
    0.45
    HtmlAttribute
    0.45
    поль
    0.44
    Act Density 0.004%

    No Known Activations