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

    Neuronpedia

    INDEX
    Explanations

    ==

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the “==” equality comparison operator.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    printed
    -0.07
     Gill
    -0.07
    stackpath
    -0.07
    lland
    -0.07
    љ
    -0.07
     ing
    -0.07
    gulp
    -0.07
    Pers
    -0.07
    lit
    -0.07
    not
    -0.07
    POSITIVE LOGITS
     ==
    0.11
    ==
    0.10
    ()==
    0.10
    ")==
    0.08
    amo
    0.08
    .face
    0.07
    ίναι
    0.07
     mean
    0.07
    AA
    0.07
    ']=="
    0.07
    Act Density 0.017%

    No Known Activations