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

    Neuronpedia

    INDEX
    Explanations

    Tomorrow

    np_max-act · gemini-2.0-flash

    The neuron is highly specialized to detect occurrences of the word “Tomorrow.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     handful
    -0.08
    인
    -0.07
     counts
    -0.07
     basın
    -0.07
     wealthy
    -0.07
    	Duel
    -0.07
    _in
    -0.07
    ain
    -0.06
    Coins
    -0.06
     Cul
    -0.06
    POSITIVE LOGITS
     tomorrow
    0.16
     Tomorrow
    0.12
    Tomorrow
    0.12
     Morrow
    0.08
    moment
    0.07
     will
    0.07
    269
    0.07
     yesterday
    0.07
    568
    0.07
    ovsky
    0.07
    Act Density 0.009%

    No Known Activations