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

    Neuronpedia

    INDEX
    Explanations

    Named entities

    np_max-act · gemini-2.0-flash

    This neuron primarily activates on proper nouns—names of people, places, or organizations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Judiciary
    -0.07
     mug
    -0.07
    जब
    -0.06
    .inline
    -0.06
     тради
    -0.06
    igm
    -0.06
     restricting
    -0.06
     fod
    -0.06
    Ups
    -0.06
    UP
    -0.06
    POSITIVE LOGITS
    	atomic
    0.07
    +'/
    0.07
     IllegalAccessException
    0.06
    -watch
    0.06
    _sep
    0.06
     Boris
    0.06
    "]==
    0.06
    ,strlen
    0.06
    <!--<
    0.06
    　ヽ
    0.06
    Act Density 0.060%

    No Known Activations