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

    Neuronpedia

    INDEX
    Explanations

    completion

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of “completion” callback parameters or completion‐handler arguments in function or method calls.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     �
    -0.06
    舌
    -0.06
    記
    -0.06
    _seq
    -0.06
     ні
    -0.06
     instance
    -0.06
     takeaway
    -0.06
     commons
    -0.06
     条
    -0.06
     股
    -0.06
    POSITIVE LOGITS
    placer
    0.07
     listener
    0.07
    Assembler
    0.07
     Krist
    0.07
    ína
    0.06
     misdemean
    0.06
    evil
    0.06
    .build
    0.06
     Fehler
    0.06
    (Settings
    0.06
    Act Density 0.001%

    No Known Activations