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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens representing floating-point values (decimal numbers with a fractional part).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _python
    -0.07
     Kürt
    -0.07
     �
    -0.07
     прод
    -0.06
     clic
    -0.06
     yaklaş
    -0.06
     Doe
    -0.06
    -thread
    -0.06
     eSports
    -0.06
     họa
    -0.06
    POSITIVE LOGITS
    о
    0.07
     Би
    0.06
    .Inner
    0.06
     �
    0.06
    TEMP
    0.06
    .Use
    0.06
    ubs
    0.06
    .setRequest
    0.06
    GroupBox
    0.06
    ВО
    0.06
    Act Density 0.206%

    No Known Activations