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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash

    The neuron activates on the negative adverb “not.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    tadır
    -0.07
    いの
    -0.07
    would
    -0.07
    (inputStream
    -0.07
    .have
    -0.07
     plá
    -0.07
     Страна
    -0.07
    FilterWhere
    -0.07
    upakan
    -0.07
    CHEDULE
    -0.07
    POSITIVE LOGITS
    (not
    0.06
     지나
    0.06
     Forgotten
    0.06
    ыџN
    0.06
    759
    0.06
     graf
    0.06
     Sniper
    0.06
    服
    0.06
    خط
    0.06
     nun
    0.06
    Act Density 0.004%

    No Known Activations