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

    Neuronpedia

    INDEX
    Explanations

    syntactical structures or symbols in code

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

    symbols and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.44
    ẨM
    -0.44
     Apel
    -0.41
    ppuden
    -0.41
    AsStream
    -0.40
    囊
    -0.40
    ualaikum
    -0.40
    }{*}{
    -0.40
     ev
    -0.39
     JUGA
    -0.39
    POSITIVE LOGITS
    [];
    2.27
    [];

    1.55
     [];
    1.15
    []);
    1.11
    ?;
    1.00
     []);
    0.93
    ([]);
    0.90
     [];

    0.88
    [].
    0.87
    !;
    0.86
    Act Density 0.002%
    No Known Activations