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

    Neuronpedia

    INDEX
    Explanations

    punctuation, specifically the comma

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

    Follows a question mark "Q" or concerns an experiment

    np_acts-logits-general · gemini-2.0-flash

    questions and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rolment
    -0.67
    WebServlet
    -0.64
    rawDesc
    -0.62
    abetta
    -0.54
    ‘‘
    -0.54
     pensado
    -0.54
     стаття
    -0.54
    jsdelivr
    -0.54
     ‘
    -0.53
    =’
    -0.53
    POSITIVE LOGITS
     \#
    0.73
     \&
    0.68
    \\
    0.64
    \#
    0.63
     Metropolitana
    0.59
     withheld
    0.59
    :\\
    0.59
     \#:
    0.59
     \%
    0.57
     Thebes
    0.57
    Act Density 0.312%

    No Known Activations