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

    Neuronpedia

    INDEX
    Explanations

    Parenthesis/brackets

    np_max-act · gemini-2.0-flash

    This neuron detects numeric literals (especially floating-point numbers) in code snippets.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ceph
    -0.07
     CGPointMake
    -0.06
    asto
    -0.06
     FOR
    -0.06
    itor
    -0.06
     Gingrich
    -0.06
    \Container
    -0.06
     counterfeit
    -0.06
    ison
    -0.06
    Connor
    -0.06
    POSITIVE LOGITS
    =current
    0.07
     trời
    0.07
    .segments
    0.07
    ımda
    0.06
     herk
    0.06
     должна
    0.06
     lightly
    0.06
     russe
    0.06
    다는
    0.06
     descri
    0.06
    Act Density 0.023%

    No Known Activations