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

    Neuronpedia

    INDEX
    Explanations

    Dates

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens—especially dates, measurements, and other number sequences.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    áty
    -0.07
     DOI
    -0.06
    환
    -0.06
    感じ
    -0.06
     pathetic
    -0.06
    ại
    -0.06
     userData
    -0.06
     ayrı
    -0.06
    aksi
    -0.06
    uis
    -0.06
    POSITIVE LOGITS
     Nex
    0.07
    ('|
    0.07
    OSH
    0.06
     strengthened
    0.06
    _vc
    0.06
     Trends
    0.06
    ]("
    0.06
    Dub
    0.06
    (float
    0.06
    (valor
    0.06
    Act Density 0.484%

    No Known Activations