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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric constants (literal numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    чих
    -0.07
    RequestParam
    -0.07
     å
    -0.07
     Granite
    -0.06
     Blanco
    -0.06
    DNS
    -0.06
    buf
    -0.06
    alue
    -0.06
    				
↵
    -0.06
    strike
    -0.06
    POSITIVE LOGITS
     Дмит
    0.06
     HinderedRotor
    0.06
    CLUDING
    0.06
     проводить
    0.06
     createdBy
    0.06
     neoliberal
    0.06
     embarrassing
    0.06
    entieth
    0.06
     ジ
    0.06
     promotion
    0.06
    Act Density 0.057%

    No Known Activations