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

    Neuronpedia

    INDEX
    Explanations

    special characters or punctuation used within sentences

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

    acronyms or abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plufieurs
    -0.52
     theme
    -0.48
     enfans
    -0.48
     reputación
    -0.47
     THEME
    -0.47
    aktery
    -0.47
     fevere
    -0.47
     bőr
    -0.47
     meditación
    -0.46
     themſelves
    -0.45
    POSITIVE LOGITS
     autorytatywna
    0.84
    Autoritní
    0.56
     Autorisations
    0.43
    EndInit
    0.42
    Thx
    0.42
    ￡
    0.42
    =$?
    0.41
     acronym
    0.41
    XCTAssertEqual
    0.40
    IC
    0.40
    Act Density 0.558%

    No Known Activations