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

    Neuronpedia

    INDEX
    Explanations

    to/top

    np_max-act · gemini-2.0-flash

    This neuron fires strongly on the occurrences (and sub‐tokens) of the mathematical term “polytope.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    、これ
    -0.07
    .Column
    -0.07
     closer
    -0.06
    .AsyncTask
    -0.06
     Ferrari
    -0.06
     negligible
    -0.06
     scn
    -0.06
     War
    -0.06
    ीकरण
    -0.06
    girls
    -0.06
    POSITIVE LOGITS
    atables
    0.07
     submitting
    0.07
    .Lib
    0.06
    -seeking
    0.06
     Brewing
    0.06
    owego
    0.06
     salle
    0.06
    -mod
    0.06
    IDA
    0.06
     eth
    0.06
    Act Density 0.004%

    No Known Activations