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

    Neuronpedia

    INDEX
    Explanations

    Code and dates

    np_max-act · gemini-2.0-flash

    The neuron is essentially dead—it never activates on any token.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    26
    -0.07
     monkeys
    -0.07
    Grand
    -0.06
     panorama
    -0.06
     silenced
    -0.06
     lure
    -0.06
    _ops
    -0.06
    _CR
    -0.06
    	ds
    -0.06
    ड
    -0.06
    POSITIVE LOGITS
     ошиб
    0.07
     铁
    0.06
     ساخت
    0.06
     Massive
    0.06
    .Load
    0.06
    ]>↵
    0.06
    ับต
    0.06
    Nu
    0.06
    彡
    0.06
     renovations
    0.06
    Act Density 0.040%

    No Known Activations