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

    Neuronpedia

    INDEX
    Explanations

    conclusion

    np_max-act · gemini-2.0-flash

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

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    oma
    -0.07
    aurus
    -0.07
    ious
    -0.07
    ды
    -0.07
    alette
    -0.07
    ाम
    -0.07
     trauma
    -0.07
    ника
    -0.07
    _constraints
    -0.07
     militants
    -0.07
    POSITIVE LOGITS
     sortable
    0.07
    _contin
    0.07
     alles
    0.06
     pensar
    0.06
     probl
    0.06
    _aw
    0.06
    Conclusion
    0.06
     उपलब
    0.06
     �
    0.06
     Synopsis
    0.06
    Act Density 0.004%

    No Known Activations