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

    Neuronpedia

    INDEX
    Explanations

    API errors

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens and numeric expressions (digits, dates, and numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .output
    -0.07
     statistics
    -0.06
    _chain
    -0.06
    730
    -0.06
    cancel
    -0.06
    	response
    -0.06
     Browse
    -0.06
     //
    -0.06
    software
    -0.06
     dus
    -0.06
    POSITIVE LOGITS
    ltra
    0.06
    ROME
    0.06
    _GRE
    0.06
    rome
    0.06
    exampleInputEmail
    0.06
     بي
    0.06
     españ
    0.06
    .getFirst
    0.06
    assertInstanceOf
    0.06
    ści
    0.06
    Act Density 0.056%

    No Known Activations