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

    Neuronpedia

    INDEX
    Explanations

    sports betting predictions

    np_max-act · gemini-2.0-flash

    This neuron detects the special header tokens marking the beginning of an assistant response (e.g. the “<|start_header_id|> assistant <|end_header_id|>” sequence).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     billionaires
    -0.07
     мен
    -0.07
     kter
    -0.07
     volunteering
    -0.06
     Carson
    -0.06
    ،
    -0.06
     apprentices
    -0.06
    ediği
    -0.06
    786
    -0.06
    749
    -0.06
    POSITIVE LOGITS
     always
    0.07
    Tambah
    0.07
    に対
    0.06
     Dos
    0.06
    stial
    0.06
     Picks
    0.06
     Nem
    0.06
    Dos
    0.06
    oples
    0.06
    Describe
    0.06
    Act Density 0.019%

    No Known Activations