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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods

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

    File extensions after a period

    np_acts-logits-general · gemini-2.0-flash

    image file extensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.76
    ,
    -0.68
     is
    -0.52
    …
    -0.49
     in
    -0.48
     of
    -0.47
     on
    -0.47
     and
    -0.47
    ↵
    -0.46
    -
    -0.46
    POSITIVE LOGITS
    Portail
    0.95
    AsUp
    0.94
     AssemblyCompany
    0.92
     виправивши
    0.89
    RTEE
    0.89
    ]--;
    0.86
    webElementXpaths
    0.86
     purpoſe
    0.85
     cherchés
    0.85
     Савезне
    0.85
    Act Density 0.121%

    No Known Activations