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

    Neuronpedia

    INDEX
    Explanations

    abstract representations of data structures and their properties in programming contexts

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

    Comes after a colon

    np_acts-logits-general · gemini-2.0-flash

    name and value pairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ()]);
    -0.59
    _))
    -0.52
    mej
    -0.49
    )");
    -0.48
    EXPRESSION
    -0.48
     {}),
    -0.47
    }/${
    -0.46
    >");
    -0.46
     />);
    -0.46
    LError
    -0.45
    POSITIVE LOGITS
    「
    1.55
     "
    1.46
     «
    1.31
    ("
    1.28
     '
    1.27
     「
    1.26
     “
    1.25
     „
    1.25
    :@"
    1.23
    ('
    1.20
    Act Density 0.682%

    No Known Activations