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

    Neuronpedia

    INDEX
    Explanations

    sections and organization within documents, particularly references to parts, volumes, and chapters

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

    Parts, phases, volumes, chapters, seasons

    np_acts-logits-general · gemini-2.0-flash

    sections and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.87
    GEBURTSDATUM
    -0.85
    RegistryLite
    -0.76
     snippetHide
    -0.74
    ArrowToggle
    -0.72
     protoimpl
    -0.71
    دانشنامهٔ
    -0.64
    ьаж
    -0.63
     समीक्षाओं
    -0.62
    帖最后由
    -0.62
    POSITIVE LOGITS
    ersen
    0.59
     two
    0.54
     III
    0.51
     three
    0.50
     one
    0.50
     eins
    0.48
     кӀош
    0.48
     II
    0.47
     Bij
    0.47
     IV
    0.46
    Act Density 0.546%

    No Known Activations