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

    Neuronpedia

    INDEX
    Explanations

    two

    np_max-act · gemini-2.0-flash

    This neuron activates primarily on numerical tokens (digits or number words).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    еві
    -0.07
    NH
    -0.06
    icher
    -0.06
    aniu
    -0.06
     Similarly
    -0.06
    CHED
    -0.06
     teas
    -0.06
    icked
    -0.06
    Utc
    -0.06
     ingr
    -0.06
    POSITIVE LOGITS
     JOptionPane
    0.07
     mailing
    0.06
    bedPane
    0.06
    .Serializable
    0.06
     scary
    0.06
    attendance
    0.06
     intending
    0.06
     waived
    0.06
     Waiting
    0.06
    .getChild
    0.06
    Act Density 0.033%

    No Known Activations