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

    Neuronpedia

    INDEX
    Explanations

    patterns related to comparisons or equality checks in code

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

    comparison and assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PDC
    -0.49
    .」
    -0.45
     DHS
    -0.43
     BPS
    -0.43
    ）』
    -0.41
     PSP
    -0.41
    linger
    -0.40
     TSA
    -0.40
     RDA
    -0.39
    ipelago
    -0.39
    POSITIVE LOGITS
     ==
    2.11
    ==
    1.50
     ===
    1.45
    ]==
    1.39
    ()==
    1.34
    )==
    1.31
    ']==
    1.22
     !=
    1.15
    ==-
    1.13
    ==$
    1.09
    Act Density 0.019%

    No Known Activations