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

    Neuronpedia

    INDEX
    Explanations

    These

    np_max-act · gemini-2.0-flash

    The neuron fires on numeral characters or numeric tokens (digits and numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Posts
    -0.06
     graphene
    -0.06
    tx
    -0.06
     LG
    -0.06
     Embedded
    -0.06
     reactors
    -0.06
     gå
    -0.06
    \":\"
    -0.06
    pedido
    -0.06
    .weapon
    -0.06
    POSITIVE LOGITS
     massasje
    0.06
     typealias
    0.06
    enuine
    0.06
     giám
    0.06
     eskorte
    0.06
     sights
    0.06
     regulates
    0.06
    ::.
    0.06
    ..↵
    0.06
     وصلات
    0.06
    Act Density 0.066%

    No Known Activations