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

    Neuronpedia

    INDEX
    Explanations

    missed

    np_max-act · gemini-2.0-flash

    This neuron responds to mentions of things being “missed” (i.e. failures or error rates in detection tasks).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    redirect
    -0.07
    	dev
    -0.06
    .getMax
    -0.06
    стер
    -0.06
    -it
    -0.06
    .combine
    -0.06
    sah
    -0.06
    composite
    -0.06
    repeat
    -0.06
    .ab
    -0.06
    POSITIVE LOGITS
     Failed
    0.06
    dao
    0.06
    姓名
    0.06
    _slots
    0.06
     мене
    0.06
    为什么
    0.06
     شود
    0.06
    (--
    0.06
    文献
    0.06
     huge
    0.06
    Act Density 0.019%

    No Known Activations