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

    Neuronpedia

    INDEX
    Explanations

    -ci

    np_max-act · gemini-2.0-flash

    This neuron detects references to CI/build status badges (e.g. “travis-ci”) in project README headers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ك
    -0.07
    _IMETHOD
    -0.07
    Bru
    -0.07
    循
    -0.07
     specifics
    -0.07
    (blog
    -0.07
    甚
    -0.06
    (Index
    -0.06
     Petro
    -0.06
    .Rows
    -0.06
    POSITIVE LOGITS
    -ci
    0.07
    mall
    0.07
    izi
    0.06
     crafted
    0.06
    metros
    0.06
    0.06
    .co
    0.06
    alted
    0.06
    един
    0.06
     encontrar
    0.06
    Act Density 0.000%

    No Known Activations