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

    Neuronpedia

    INDEX
    Explanations

    Teaching

    np_max-act · gemini-2.0-flash

    The neuron activates on text describing “Solving issues with real-time or external data,” i.e., mentions of handling real-time/external data problems.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     구글
    -0.07
    conomy
    -0.06
    -स
    -0.06
    ิกายน
    -0.06
    .picture
    -0.06
    ريل
    -0.06
    ii
    -0.06
     nombreux
    -0.06
     dvou
    -0.06
    -Con
    -0.06
    POSITIVE LOGITS
     physics
    0.07
     prostor
    0.07
     matter
    0.06
     alan
    0.06
     complet
    0.06
    -writing
    0.06
    ฉ
    0.06
     gost
    0.06
     وع
    0.06
     scoped
    0.06
    Act Density 0.001%

    No Known Activations