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

    Neuronpedia

    INDEX
    Explanations

    calculate

    np_max-act · gemini-2.0-flash

    This neuron activates on floating-point numeric tokens (decimal numbers in calculations).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Stan
    -0.07
     bus
    -0.07
     Parade
    -0.07
     Cruise
    -0.07
     transit
    -0.06
    -blood
    -0.06
     Transit
    -0.06
    	expect
    -0.06
    Amazon
    -0.06
     contar
    -0.06
    POSITIVE LOGITS
    Ι
    0.06
    ingles
    0.06
    "http
    0.06
    (models
    0.06
    ██
    0.06
    очки
    0.06
    นวย
    0.06
     AJ
    0.06
     meu
    0.05
    etrize
    0.05
    Act Density 0.035%

    No Known Activations