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

    Neuronpedia

    INDEX
    Explanations

    named

    np_max-act · gemini-2.0-flash

    The neuron activates on instances of the word “named.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    frage
    -0.07
    ительно
    -0.07
    (con
    -0.07
     Can
    -0.07
     go
    -0.07
    -stop
    -0.07
     do
    -0.07
    been
    -0.07
    دیگر
    -0.07
    	check
    -0.07
    POSITIVE LOGITS
     named
    0.10
    named
    0.09
     titled
    0.09
     unauthorized
    0.08
     Named
    0.08
     gifted
    0.07
    ured
    0.07
     Signed
    0.07
     knit
    0.06
    ed
    0.06
    Act Density 0.017%

    No Known Activations