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

    Neuronpedia

    INDEX
    Explanations

    List

    np_max-act · gemini-2.0-flash

    This neuron detects Go type identifiers (CamelCase names starting with an uppercase letter).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ↵            ↵
    -0.07
    ↵			↵
    -0.07
     gave
    -0.06
    Tuy
    -0.06
    。我
    -0.06
     asteroids
    -0.06
     Auf
    -0.06
    忙
    -0.06
     grams
    -0.06
     teaspoon
    -0.06
    POSITIVE LOGITS
     Snap
    0.08
     aktiv
    0.08
    _FAR
    0.07
    _START
    0.07
    iones
    0.07
     CHILD
    0.07
    (parent
    0.06
    死
    0.06
    sess
    0.06
     nodeList
    0.06
    Act Density 0.005%

    No Known Activations