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

    Neuronpedia

    INDEX
    Explanations

    ignore

    np_max-act · gemini-2.0-flash

    The neuron is triggered by tokens related to someone ignoring or disregarding another (e.g. “ignore,” “ignored”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ランド
    -0.07
    enefit
    -0.06
    distinct
    -0.06
    	jQuery
    -0.06
     charcoal
    -0.06
    	product
    -0.06
    очь
    -0.06
     rock
    -0.06
    UPDATE
    -0.06
    ุงเทพ
    -0.06
    POSITIVE LOGITS
     ignore
    0.10
     ignored
    0.09
     ignoring
    0.09
     Ignore
    0.08
     mun
    0.07
     ignores
    0.07
    _ISO
    0.06
    ignore
    0.06
    animate
    0.06
    verted
    0.06
    Act Density 0.011%

    No Known Activations