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

    Neuronpedia

    INDEX
    Explanations

    nightmare

    np_max-act · gemini-2.0-flash

    This neuron specifically fires on the word “nightmare” (and closely related dark-theme terms).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Operand
    -0.07
    icích
    -0.06
    _fsm
    -0.06
     revenues
    -0.06
    Trivia
    -0.06
    .:.:.:.:
    -0.06
     facebook
    -0.06
    aggable
    -0.06
    :@
    -0.06
    ["@
    -0.06
    POSITIVE LOGITS
     nightmare
    0.11
     nightmares
    0.08
     ordeal
    0.08
     Nightmare
    0.07
    ЕР
    0.07
    -year
    0.07
    -Year
    0.07
     Career
    0.07
    maid
    0.06
     напис
    0.06
    Act Density 0.002%

    No Known Activations