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

    Neuronpedia

    INDEX
    Explanations

    band

    np_max-act · gemini-2.0-flash

    This neuron detects URL‐style protocol tokens and separators (e.g., “http”, “https”, “://”) in code or documentation.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     dess
    -0.06
    eah
    -0.06
     "=
    -0.06
    价值
    -0.06
    ][]
    -0.06
     Yas
    -0.06
     YA
    -0.06
    .Z
    -0.06
    being
    -0.06
    Spawn
    -0.06
    POSITIVE LOGITS
     identifier
    0.07
    Getting
    0.06
    �
    0.06
     mở
    0.06
     unclear
    0.06
    (In
    0.06
     almacen
    0.06
    рис
    0.06
    公开
    0.06
    分享
    0.06
    Act Density 0.323%

    No Known Activations