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 four‐digit year numbers (often appearing in dates).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ricanes
    -0.07
     heyec
    -0.07
     освещ
    -0.06
     Temper
    -0.06
     миров
    -0.06
    :boolean
    -0.06
    ератор
    -0.06
    ircle
    -0.06
    (di
    -0.06
    romě
    -0.06
    POSITIVE LOGITS
    وند
    0.07
    载
    0.07
    (chan
    0.06
    skill
    0.06
     niên
    0.06
    /trunk
    0.06
    寸
    0.06
    onclick
    0.06
     deficient
    0.06
    Short
    0.06
    Act Density 0.028%

    No Known Activations