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

    Neuronpedia

    INDEX
    Explanations

    quantitative or numerical data in a formal context

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

    Followed by numbers or claims

    np_acts-logits-general · gemini-2.0-flash

    legal citations and statutes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Stu
    -0.60
    Stu
    -0.55
    ]--;
    -0.54
    tito
    -0.52
     Sta
    -0.46
    spar
    -0.44
    gut
    -0.44
    vably
    -0.43
    olver
    -0.43
    AccessFile
    -0.43
    POSITIVE LOGITS
     transférez
    0.76
    awaiter
    0.64
    \
    0.63
    awtextra
    0.62
     snippetHide
    0.61
    findpost
    0.59
     rains
    0.58
    httphttps
    0.58
     vuitton
    0.58
     cherchés
    0.58
    Act Density 0.052%

    No Known Activations