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

    Neuronpedia

    INDEX
    Explanations

    seats

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens—particularly digits denoting counts (e.g. seat numbers, years, ages) in election‐result contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     stringWith
    -0.07
    igo
    -0.06
     wür
    -0.06
    RefCount
    -0.06
     dwarf
    -0.06
    (rb
    -0.06
    inz
    -0.06
     elementary
    -0.05
    .fore
    -0.05
    ассив
    -0.05
    POSITIVE LOGITS
    _exists
    0.07
     Ramsey
    0.07
    =batch
    0.07
    reasonable
    0.07
     Keys
    0.06
    径
    0.06
     سوال
    0.06
    -cols
    0.06
     lain
    0.06
     เจ
    0.06
    Act Density 0.007%

    No Known Activations