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

    Neuronpedia

    INDEX
    Explanations

    prime number code

    np_max-act · gemini-2.0-flash

    This neuron is effectively inactive and does not detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Paths
    -0.07
    итов
    -0.06
    .]↵↵
    -0.06
     Stores
    -0.06
     Nintendo
    -0.06
    빌
    -0.06
     Penguin
    -0.06
    >
↵
↵
    -0.06
     ADC
    -0.06
     Cast
    -0.06
    POSITIVE LOGITS
    辰
    0.07
     gw
    0.07
     elems
    0.07
     ado
    0.06
    _gc
    0.06
    یزات
    0.06
    abcdefghijkl
    0.06
    ornment
    0.06
    *out
    0.06
    (argument
    0.06
    Act Density 0.008%

    No Known Activations