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

    Neuronpedia

    INDEX
    Explanations

    perfect

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “perfect” in references to perfect tenses.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ledge
    -0.06
     renovation
    -0.06
    _ENTRY
    -0.06
     realization
    -0.06
     propane
    -0.06
     огра
    -0.06
     कल
    -0.06
     SSA
    -0.06
    /System
    -0.06
     trad
    -0.06
    POSITIVE LOGITS
    _ps
    0.07
    SplitOptions
    0.07
     Основ
    0.06
     Venture
    0.06
     jwt
    0.06
    蜘蛛词
    0.06
    add
    0.06
    fullname
    0.06
    _lista
    0.06
    	trigger
    0.06
    Act Density 0.002%

    No Known Activations