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

    Neuronpedia

    INDEX
    Explanations

    the end of code blocks in structured text

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

    code block endings and assertions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MainAxisSize
    -0.77
     queſta
    -0.73
     ब्रेकडाउन
    -0.71
     intptr
    -0.67
    tanleria
    -0.66
     oprot
    -0.65
    linawan
    -0.63
     Мексичка
    -0.61
     increí
    -0.60
     Geſch
    -0.60
    POSITIVE LOGITS
    ↵↵
    0.43
    <eos>
    0.41
    ApplicationTests
    0.38
    test
    0.38
    subsubsection
    0.36
    CONT
    0.36
    ↵
    0.35
    permitAll
    0.35
     Où
    0.35
    //
    0.35
    Act Density 0.003%

    No Known Activations