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

    Neuronpedia

    INDEX
    Explanations

    never

    np_max-act · gemini-2.0-flash

    The neuron consistently activates on the word “never,” especially in first-person statements about something not done before.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     RECEIVE
    -0.07
     ticker
    -0.07
     Earn
    -0.07
     quiz
    -0.06
    _parsed
    -0.06
     Become
    -0.06
    repair
    -0.06
     earned
    -0.06
     earns
    -0.06
     منزل
    -0.06
    POSITIVE LOGITS
    pest
    0.06
     Separator
    0.06
    Ú
    0.06
    Ju
    0.06
    _Renderer
    0.06
     startDate
    0.06
    非
    0.06
    /non
    0.06
     hran
    0.06
     noen
    0.06
    Act Density 0.012%

    No Known Activations