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

    Neuronpedia

    INDEX
    Explanations

    quotes and punctuation within text

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

    Code or data delimiters

    np_acts-logits-general · gemini-2.0-flash

    code syntax and data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TProtocol
    -0.78
    [::-
    -0.74
    anzo
    -0.74
    vastava
    -0.73
     ')[
    -0.73
     Gries
    -0.72
     $_[
    -0.70
    Oise
    -0.69
    hø
    -0.68
     هيا
    -0.68
    POSITIVE LOGITS
    %"
    0.93
    /*"
    0.83
    /"
    0.83
    )"
    0.83
    |"
    0.81
     ")"
    0.80
    '"
    0.80
    ："
    0.80
    ]"
    0.79
    ="#"
    0.78
    Act Density 0.123%

    No Known Activations