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

    Neuronpedia

    INDEX
    Explanations

    HTML-like tags that denote collapsible sections in code documentation

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

    code folding markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ExtendWith
    -0.64
     CreateTagHelper
    -0.59
    GOTREF
    -0.44
    BufferException
    -0.44
     createState
    -0.42
     StatelessWidget
    -0.42
     webdriver
    -0.40
    bootstrapcdn
    -0.39
     Dilemma
    -0.39
    SBATCH
    -0.39
    POSITIVE LOGITS
     betweenstory
    0.54
     endregion
    0.45
    EndProject
    0.43
     assurent
    0.41
    <?
    0.41
    endregion
    0.41
    afficheront
    0.41
    Последние
    0.40
    ⓧ
    0.40
     Below
    0.40
    Act Density 0.076%

    No Known Activations