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

    Neuronpedia

    INDEX
    Explanations

    conditions and comparisons in programming logic

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

    Code syntax: commas, equality checks, and string handling

    np_acts-logits-general · gemini-2.0-flash

    empty string ""

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     {},
    -0.61
    AddTagHelper
    -0.57
    ');
    -0.57
    );
    -0.56
    ftagPool
    -0.56
     [],
    -0.55
    ;
    -0.51
    بوابة
    -0.51
    )];
    -0.50
    )
    -0.50
    POSITIVE LOGITS
     ""
    1.17
    ""
    1.00
     ''
    1.00
     "",
    0.98
     "";
    0.92
    =""
    0.87
    EmptyString
    0.84
     "")
    0.83
    ("")
    0.81
     '',
    0.79
    Act Density 0.157%

    No Known Activations