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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash

    This neuron detects numeric literal tokens (especially floating-point numbers) in JSON or code snippets.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     cruiser
    -0.07
     cruis
    -0.07
     Shelby
    -0.06
     Canadiens
    -0.06
    xae
    -0.06
     filles
    -0.06
     Bud
    -0.06
    nodiscard
    -0.06
     AIDS
    -0.06
    كار
    -0.06
    POSITIVE LOGITS
    惊
    0.07
    Impact
    0.07
     �
    0.07
    .shopping
    0.07
     UserManager
    0.06
     ulož
    0.06
    Et
    0.06
    osit
    0.06
    rowCount
    0.06
    inherits
    0.06
    Act Density 0.035%

    No Known Activations