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

    Neuronpedia

    INDEX
    Explanations

    apostrophe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     appreh
    -0.07
    先天
    -0.07
    抱团
    -0.07
    怜
    -0.07
    幸好
    -0.07
     kata
    -0.06
    تحمل
    -0.06
    匆匆
    -0.06
    不太
    -0.06
     though
    -0.06
    POSITIVE LOGITS
     Chart
    0.07
    =$(
    0.07
    Cx
    0.07
    燃烧
    0.07
     Alberto
    0.07
    🦐
    0.07
    ////////////////////////////////////////////////
    0.07
     Random
    0.06
     basın
    0.06
    Sheet
    0.06
    Act Density 0.001%

    No Known Activations