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

    Neuronpedia

    INDEX
    Explanations

    percent

    np_max-act · gemini-2.0-flash

    This neuron never activates on any token, so it does not detect or respond to any specific content.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Mazda
    -0.07
    (dist
    -0.06
     cJSON
    -0.06
     parten
    -0.06
     gam
    -0.06
    (right
    -0.06
     định
    -0.06
    dzi
    -0.06
    يج
    -0.06
    .APP
    -0.06
    POSITIVE LOGITS
    ivated
    0.07
     Sources
    0.06
     incoming
    0.06
    nip
    0.06
    εί
    0.06
    优
    0.06
     toArray
    0.06
    *↵
    0.06
    uş
    0.06
    皮
    0.06
    Act Density 0.009%

    No Known Activations