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

    Neuronpedia

    INDEX
    Explanations

    Cup

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of “Cup” (and its language‐specific variants) in the names of cup competitions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ineTransform
    -0.07
     aboard
    -0.07
     bereits
    -0.07
    aversal
    -0.06
     �
    -0.06
    .svg
    -0.06
     livest
    -0.06
     부
    -0.06
     Hollande
    -0.06
     الخاصة
    -0.06
    POSITIVE LOGITS
     پي
    0.07
     праці
    0.07
    -thinking
    0.06
    のお
    0.06
     cider
    0.06
     recurse
    0.06
    uggested
    0.06
    _geometry
    0.06
    common
    0.06
     Troll
    0.06
    Act Density 0.006%

    No Known Activations