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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    θο
    -0.07
     rhyth
    -0.07
     ton
    -0.07
    BUY
    -0.07
     thaimassage
    -0.07
    (widget
    -0.07
     �
    -0.06
    asting
    -0.06
    eve
    -0.06
    bst
    -0.06
    POSITIVE LOGITS
     حل
    0.06
    som
    0.06
    貴
    0.06
    裕
    0.06
    时
    0.06
     çocuk
    0.06
     khiến
    0.06
     Lottery
    0.06
    新
    0.05
     kiểu
    0.05
    Act Density 0.007%

    No Known Activations