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

    Neuronpedia

    INDEX
    Explanations

    Punctuation/Conversational beginnings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gv
    -0.07
     округ
    -0.07
     손을
    -0.06
    ').'
    -0.06
    ována
    -0.06
    lug
    -0.06
     sexdate
    -0.06
    acteria
    -0.06
    ')?>
    -0.06
    项目
    -0.06
    POSITIVE LOGITS
    =output
    0.08
     Paras
    0.07
     thorough
    0.06
     welt
    0.06
     wherein
    0.06
     neu
    0.06
     ทาง
    0.06
    竹
    0.06
     weird
    0.06
     DIS
    0.06
    Act Density 0.056%

    No Known Activations