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

    Neuronpedia

    INDEX
    Explanations

    Protests and strikes

    np_max-act · gemini-2.0-flash

    The neuron is triggered by numeric expressions—digits, quantities, durations, distances, percentages, etc.—in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Van
    -0.07
     messages
    -0.06
    eným
    -0.06
    这种
    -0.06
    .Common
    -0.06
    TRS
    -0.06
    (GL
    -0.06
     Depend
    -0.06
     Yugoslavia
    -0.06
     dedicate
    -0.06
    POSITIVE LOGITS
     dentro
    0.07
    elly
    0.06
    打开
    0.06
     curtains
    0.06
     perso
    0.06
    çois
    0.06
     pequ
    0.06
    -num
    0.06
     považ
    0.06
     läng
    0.06
    Act Density 0.013%

    No Known Activations