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

    Neuronpedia

    INDEX
    Explanations

    United States

    np_max-act · gemini-2.0-flash

    This neuron primarily activates on proper names and titles—i.e. capitalized named entities such as authors, publications, and person or organization names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Vi
    -0.07
    _TE
    -0.07
    manage
    -0.07
     belief
    -0.07
     GAME
    -0.06
    Workbook
    -0.06
     kinh
    -0.06
     subroutine
    -0.06
     TEAM
    -0.06
    Particle
    -0.06
    POSITIVE LOGITS
    ->{_
    0.07
    -normal
    0.07
    .createObject
    0.06
    ó
    0.06
    される
    0.06
    theast
    0.06
    pta
    0.06
    cdecl
    0.06
    .assertNot
    0.06
     bouts
    0.06
    Act Density 0.013%

    No Known Activations