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

    Neuronpedia

    INDEX
    Explanations

    dataprovider

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the “@dataProvider” annotation (and closely related doc‐comment tokens) in test code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ]/
    -0.07
    Dog
    -0.07
    >#
    -0.07
    CLUS
    -0.07
     events
    -0.06
     EVENTS
    -0.06
     сп
    -0.06
     Rise
    -0.06
    ,$
    -0.06
     Boy
    -0.06
    POSITIVE LOGITS
     reluctant
    0.07
    recognized
    0.06
     Valencia
    0.06
     dared
    0.06
    powered
    0.06
     acted
    0.06
     subsidized
    0.06
     originate
    0.06
     midfield
    0.06
    ern
    0.06
    Act Density 0.004%

    No Known Activations