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

    Neuronpedia

    INDEX
    Explanations

    ignore or disregard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lemons
    0.43
     mishaps
    0.39
     heritage
    0.38
    িল
    0.38
     lemonade
    0.37
     Withers
    0.37
     মার্
    0.36
     болез
    0.36
    ंड
    0.36
     চলুন
    0.36
    POSITIVE LOGITS
     ignored
    0.93
     ignore
    0.92
    忽略
    0.88
    ignored
    0.82
    ignore
    0.82
    Ignore
    0.79
     disregarded
    0.77
     Ignore
    0.77
     ignores
    0.75
     disregard
    0.72
    Act Density 0.000%

    No Known Activations