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

    Neuronpedia

    INDEX
    Explanations

    affection

    np_max-act · gemini-2.0-flash

    The neuron activates on descriptive words that highlight a pet’s warm, friendly, and sociable qualities (e.g. affectionate, playful, gentle, good with children).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     concludes
    -0.07
    aks
    -0.07
    inds
    -0.07
    кі
    -0.06
    aland
    -0.06
     dbContext
    -0.06
     soul
    -0.06
    ós
    -0.06
    iking
    -0.06
    	that
    -0.06
    POSITIVE LOGITS
     Disconnect
    0.07
     останов
    0.07
    .Custom
    0.06
    (userid
    0.06
    (access
    0.06
    .pre
    0.06
     scrambled
    0.06
    .setString
    0.06
     getActivity
    0.06
     gag
    0.06
    Act Density 0.012%

    No Known Activations