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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron never fires—it doesn’t detect or match any tokens in these code excerpts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     CCD
    -0.07
    OGLE
    -0.06
     문의
    -0.06
     jail
    -0.06
    .rf
    -0.06
    urus
    -0.06
     목소
    -0.06
     розвитку
    -0.06
    ungeons
    -0.06
    egot
    -0.06
    POSITIVE LOGITS
    //----------------
    0.07
     calm
    0.06
     saya
    0.06
     adamant
    0.06
    (stage
    0.06
     Cob
    0.06
     blessed
    0.06
     dieta
    0.06
    	Local
    0.06
     sworn
    0.06
    Act Density 0.015%

    No Known Activations