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

    Neuronpedia

    INDEX
    Explanations

    swap

    np_max-act · gemini-2.0-flash

    This neuron fires on occurrences of the identifier “swap,” i.e. when the text names a function or variable called swap.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    entence
    -0.08
     knife
    -0.07
    .FindControl
    -0.07
     intensity
    -0.07
     concent
    -0.07
    _FIELDS
    -0.07
     Millions
    -0.07
     Pierre
    -0.07
     Concent
    -0.07
    argins
    -0.07
    POSITIVE LOGITS
     swap
    0.13
     Swap
    0.11
    swap
    0.11
    Swap
    0.11
     swapping
    0.09
     swapped
    0.09
     swaps
    0.09
    .swap
    0.08
    ?p
    0.08
    map
    0.08
    Act Density 0.003%

    No Known Activations