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

    Neuronpedia

    INDEX
    Explanations

    peanuts and peanut allergies

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect mentions of “peanut” (and its variants) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     decor
    -0.08
     st
    -0.08
     Danielle
    -0.07
     toolbar
    -0.06
     двор
    -0.06
    isle
    -0.06
    ilee
    -0.06
     худож
    -0.06
     ج
    -0.06
    214
    -0.06
    POSITIVE LOGITS
     peanut
    0.14
     Peanut
    0.13
     peanuts
    0.12
    anuts
    0.09
     coconut
    0.07
     percent
    0.07
    Intel
    0.07
    Really
    0.07
    	puts
    0.07
     emph
    0.07
    Act Density 0.001%

    No Known Activations