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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and titles

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

    Text after initials, abbreviations, or names

    np_acts-logits-general · gemini-2.0-flash

    Thierry Blu

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Monfieur
    -1.01
     Theſe
    -0.77
     ainfi
    -0.74
     Verſ
    -0.72
     Pá
    -0.67
     Lampe
    -0.67
     Jefus
    -0.66
     avoient
    -0.66
     domestiques
    -0.66
     plufieurs
    -0.64
    POSITIVE LOGITS
    hu
    0.56
     Baillargeon
    0.55
    IActionResult
    0.53
    :+:
    0.52
     saites
    0.51
     Bachchan
    0.51
    ot
    0.51
    ранже
    0.49
    audi
    0.49
    SharedDtor
    0.48
    Act Density 0.229%

    No Known Activations