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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric measurement values (especially decimals and scientific quantities) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     opportunities
    -0.07
    áh
    -0.07
    583
    -0.06
     Pep
    -0.06
     established
    -0.06
     gastric
    -0.06
     dispers
    -0.06
     gradients
    -0.06
     role
    -0.06
    }`}
    -0.06
    POSITIVE LOGITS
     Dungeons
    0.07
     Socket
    0.06
    _SE
    0.06
     खड
    0.06
     행동
    0.06
     방송
    0.06
     пока
    0.06
     türü
    0.06
    ائي
    0.06
    主题
    0.06
    Act Density 0.031%

    No Known Activations