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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash

    The neuron fires on floating-point numeric literals (numbers containing a decimal point) in the JSON.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     empez
    -0.07
     удоб
    -0.07
    Krist
    -0.06
     Wagner
    -0.06
    (${
    -0.06
    кувати
    -0.06
    @testable
    -0.06
     pragmatic
    -0.06
    -checked
    -0.06
     představ
    -0.06
    POSITIVE LOGITS
    uos
    0.07
    .mod
    0.07
     Nations
    0.07
     Εξ
    0.06
     AU
    0.06
     count
    0.06
     demean
    0.06
     ju
    0.06
    (Vector
    0.06
    �
    0.06
    Act Density 0.008%

    No Known Activations