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

    Neuronpedia

    INDEX
    Explanations

    Years

    np_max-act · gemini-2.0-flash

    The neuron fires on four-digit year mentions (i.e. date references).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     نیاز
    -0.07
     zemi
    -0.07
     Tahoe
    -0.06
     unmistak
    -0.06
     proportional
    -0.06
    odus
    -0.06
     пацієн
    -0.06
     Rosenberg
    -0.06
     biraz
    -0.06
     його
    -0.06
    POSITIVE LOGITS
    validated
    0.07
    oping
    0.07
    !"
    0.07
    TED
    0.06
    0.06
    函数
    0.06
     Renew
    0.06
    Paths
    0.06
     ironically
    0.06
    OPTIONS
    0.06
    Act Density 0.028%

    No Known Activations