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

    Neuronpedia

    INDEX
    Explanations

    facts

    np_max-act · gemini-2.0-flash

    The neuron activates on Spanish terms derived from “curiosidad” (e.g. “curiosidades,” “curioso”), effectively spotting mentions of “curiosities” or “interesting facts.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _Insert
    -0.07
    @testable
    -0.07
    	pstmt
    -0.07
     billboard
    -0.07
    .getBean
    -0.06
    -0.06
    +#
    -0.06
    PRINTF
    -0.06
    리아
    -0.06
     Zig
    -0.06
    POSITIVE LOGITS
     somew
    0.08
     Tick
    0.07
     Benghazi
    0.07
     тр
    0.07
     eater
    0.07
     Aad
    0.06
     lod
    0.06
    кою
    0.06
     URLs
    0.06
     Chow
    0.06
    Act Density 0.038%

    No Known Activations