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

    Neuronpedia

    INDEX
    Explanations

    ants

    np_max-act · gemini-2.0-flash

    The neuron is specialized to detect the German word “Pflanzen” (and its subword pieces) whenever it appears in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     breakpoint
    -0.07
    .ba
    -0.07
     Harding
    -0.06
     dzi
    -0.06
     //{
↵
    -0.06
     {
↵
↵
↵
    -0.06
     bet
    -0.06
    事故
    -0.06
    archy
    -0.06
    Eigen
    -0.06
    POSITIVE LOGITS
     UNITED
    0.08
     plants
    0.07
     گیاه
    0.07
     planned
    0.07
     teor
    0.06
     tackle
    0.06
     flora
    0.06
     rooted
    0.06
     United
    0.06
     minist
    0.06
    Act Density 0.022%

    No Known Activations