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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    The neuron flags decimal number tokens (i.e. numbers containing a dot) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    pecial
    -0.07
     �
    -0.06
    Subset
    -0.06
     Fant
    -0.06
    .Items
    -0.06
    War
    -0.06
     Matchers
    -0.06
     extr
    -0.06
     Oxford
    -0.06
     many
    -0.06
    POSITIVE LOGITS
    كيل
    0.07
    ��
    0.07
    ág
    0.07
    agini
    0.06
     entitlement
    0.06
    _connector
    0.06
    érie
    0.06
    تا
    0.06
    очка
    0.06
     planner
    0.06
    Act Density 0.019%

    No Known Activations