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

    Neuronpedia

    INDEX
    Explanations

    international

    np_max-act · gemini-2.0-flash

    the neuron is triggered by numeric tokens (numbers and digit sequences).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _matrix
    -0.07
    bucket
    -0.07
    clean
    -0.07
    Rate
    -0.07
    dados
    -0.07
    ceeded
    -0.07
    yasal
    -0.06
    птом
    -0.06
    晓
    -0.06
    โลย
    -0.06
    POSITIVE LOGITS
     obsc
    0.06
     №
    0.06
     bonus
    0.06
    >J
    0.06
     Bernie
    0.06
     poll
    0.06
     height
    0.05
    )..
    0.05
     vy
    0.05
    ='',↵
    0.05
    Act Density 0.033%

    No Known Activations