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

    Neuronpedia

    INDEX
    Explanations

    bullet points

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens formatted as floating-point numbers (i.e. numbers containing a decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Qin
    -0.06
     orig
    -0.06
     Fame
    -0.06
    -0.06
     pathogens
    -0.06
     FPGA
    -0.06
     Pai
    -0.06
     expects
    -0.06
    "Now
    -0.06
    &a
    -0.06
    POSITIVE LOGITS
    curl
    0.07
    _ENABLED
    0.07
     ذکر
    0.07
    HO
    0.07
    ivamente
    0.07
    ُّ
    0.06
     кожного
    0.06
    Д
    0.06
    .ModelSerializer
    0.06
     individually
    0.06
    Act Density 0.024%

    No Known Activations