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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     resembled
    -0.07
    62
    -0.07
    eni
    -0.06
     Teh
    -0.06
    تغ
    -0.06
    -leaning
    -0.06
     forums
    -0.06
     actionPerformed
    -0.06
    क
    -0.06
    .include
    -0.06
    POSITIVE LOGITS
    ров
    0.07
     möglich
    0.06
     satış
    0.06
    コード
    0.06
     spice
    0.06
    џџ
    0.06
     Fall
    0.06
    WARDS
    0.06
     сы
    0.06
    翰
    0.06
    Act Density 0.004%

    No Known Activations