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

    Neuronpedia

    INDEX
    Explanations

    coding-related error handling and exception definitions

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

    exceptions and deprecation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BoxFit
    -0.63
    AddTagHelper
    -0.57
    OGND
    -0.52
    mtrl
    -0.50
    AnchorStyles
    -0.50
    aarrggbb
    -0.49
     Administrativna
    -0.49
     يتيمه
    -0.46
     Мексичка
    -0.45
     actionMode
    -0.45
    POSITIVE LOGITS
     occurs
    0.44
     thrown
    0.44
     assistência
    0.41
     when
    0.41
     eventuali
    0.41
    verwijspagina
    0.40
    СТВ
    0.39
     happens
    0.38
    when
    0.37
    ngdoc
    0.37
    Act Density 0.004%

    No Known Activations