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

    Neuronpedia

    INDEX
    Explanations

    rod

    np_max-act · gemini-2.0-flash

    This neuron responds to occurrences of the character sequence “rod,” as in words like “rodent,” “rod-shaped,” or “rod.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     infections
    -0.07
    _CI
    -0.07
     Marie
    -0.07
    Tai
    -0.07
    、新
    -0.07
    ريكية
    -0.07
     safe
    -0.07
     gaining
    -0.06
     бла
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     Rod
    0.13
     Rodriguez
    0.12
    Rod
    0.10
     Rodney
    0.10
     rod
    0.10
    rod
    0.09
    od
    0.09
     Hod
    0.09
     rods
    0.08
    OD
    0.08
    Act Density 0.006%

    No Known Activations