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

    Neuronpedia

    INDEX
    Explanations

    Author contributions to papers

    np_max-act · gemini-2.0-flash

    This neuron detects statements of author roles and contributions—verbs and phrases outlining who designed, conducted, wrote, reviewed, approved, or took final responsibility for the work.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     turns
    -0.06
     hello
    -0.06
    massage
    -0.06
    votes
    -0.06
     amazing
    -0.06
    _operation
    -0.06
    badge
    -0.06
     press
    -0.06
    astreet
    -0.06
    signIn
    -0.06
    POSITIVE LOGITS
    �
    0.07
    持续
    0.07
     initialise
    0.06
     dưỡng
    0.06
    InitialState
    0.06
     реб
    0.06
     onFailure
    0.06
     يا
    0.06
    भ
    0.06
     kont
    0.06
    Act Density 0.002%

    No Known Activations