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

    Neuronpedia

    INDEX
    Explanations

    memor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    還
    -0.07
    ﹏
    -0.07
    _loaded
    -0.07
    曲
    -0.07
    拽
    -0.07
     dims
    -0.07
     וגם
    -0.06
     compatible
    -0.06
    (Arg
    -0.06
     occurred
    -0.06
    POSITIVE LOGITS
    avo
    0.07
     Staten
    0.07
     ko
    0.07
    共和
    0.06
     keep
    0.06
    ださい
    0.06
    들의
    0.06
    Secretary
    0.06
    /do
    0.06
    ли
    0.06
    Act Density 0.004%

    No Known Activations