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

    Neuronpedia

    INDEX
    Explanations

    baseline

    np_max-act · gemini-2.0-flash

    The neuron activates on the term “baseline,” flagging mentions of initial or starting measurements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     verm
    -0.07
    ()(
    -0.07
     chor
    -0.07
     раздел
    -0.06
    ','".$
    -0.06
    (products
    -0.06
     //.
    -0.06
    ']").
    -0.06
    ██
    -0.06
    、、
    -0.06
    POSITIVE LOGITS
     baseline
    0.13
     lapse
    0.08
    eline
    0.08
    baseline
    0.08
    LINE
    0.07
     Garland
    0.07
    _begin
    0.07
    stocks
    0.07
    ライン
    0.07
    line
    0.06
    Act Density 0.003%

    No Known Activations