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

    Neuronpedia

    INDEX
    Explanations

    specific months

    np_max-act · gemini-2.0-flash

    The neuron chiefly fires on four-digit year tokens (i.e. date references).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    凌
    -0.06
     bugün
    -0.06
    "For
    -0.06
    Comb
    -0.06
     Bedrooms
    -0.06
     bv
    -0.06
    .XtraEditors
    -0.06
     implicitly
    -0.06
     dalle
    -0.06
    ITU
    -0.06
    POSITIVE LOGITS
     Sponsored
    0.07
    ΐ
    0.06
     pacing
    0.06
    mentor
    0.06
     stroll
    0.06
     carr
    0.06
     февраля
    0.06
     observes
    0.06
    нь
    0.06
    .getCurrentUser
    0.06
    Act Density 0.014%

    No Known Activations