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

    Neuronpedia

    INDEX
    Explanations

    accounting and negative transactions

    np_max-act · gemini-2.0-flash

    The neuron activates primarily on numeric tokens—digits, decimal points, and related symbols—i.e. it spots numbers (amounts, dates, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .alt
    -0.07
     І
    -0.06
     İmpar
    -0.06
     "@"
    -0.06
    nen
    -0.06
    _tail
    -0.06
    دان
    -0.06
     خو
    -0.06
    �
    -0.06
    .datab
    -0.05
    POSITIVE LOGITS
     rehabilit
    0.07
    (use
    0.07
     ValidationResult
    0.07
    InstanceState
    0.07
     Education
    0.07
     aug
    0.06
     Doug
    0.06
     commentator
    0.06
    κα
    0.06
     jwt
    0.06
    Act Density 0.007%

    No Known Activations