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

    Neuronpedia

    INDEX
    Explanations

    actions

    np_max-act · gemini-2.0-flash

    This neuron detects GitHub Actions workflow step definitions, especially lines with keys like “uses: actions/…”, “runs-on: …”, “jobs:”, or “name:”.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     здоров
    -0.07
    �
    -0.06
     conexión
    -0.06
    967
    -0.06
     Sword
    -0.06
     火
    -0.06
     symp
    -0.06
     Curse
    -0.06
    -Trump
    -0.06
     муз
    -0.06
    POSITIVE LOGITS
    .rotation
    0.07
     WINAPI
    0.07
    rame
    0.07
     appreciated
    0.06
     Raider
    0.06
    ;element
    0.06
    grily
    0.06
     Detail
    0.06
    brook
    0.06
     rallying
    0.06
    Act Density 0.001%

    No Known Activations