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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash

    This neuron activates on identifiers naming code types—class/struct/typedef names (e.g. CamelCase type names like AffineTransform, RigidTransform, RestoreInfo, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    638
    -0.06
    ovable
    -0.06
    withdraw
    -0.06
     дослідження
    -0.06
     Blend
    -0.06
     कहन
    -0.06
     QModelIndex
    -0.06
    today
    -0.06
     Aerospace
    -0.06
     Forbidden
    -0.06
    POSITIVE LOGITS
    imshow
    0.07
     Resolver
    0.07
     dimension
    0.06
     이전
    0.06
     dimensions
    0.06
     sic
    0.06
    _ADMIN
    0.06
    .owl
    0.06
     Phon
    0.06
    mmo
    0.06
    Act Density 0.003%

    No Known Activations