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

    Neuronpedia

    INDEX
    Explanations

    plot twists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    brengen
    -0.09
    ucumber
    -0.08
     virus
    -0.08
    ivit
    -0.08
    域
    -0.08
     viruses
    -0.08
     Viking
    -0.07
    igroup
    -0.07
     cest
    -0.07
     ಹೊರ
    -0.07
    POSITIVE LOGITS
     überras
    0.11
     پایان
    0.10
     twists
    0.10
     ending
    0.10
     শেষ
    0.09
     surprise
    0.09
     surpre
    0.09
     Ending
    0.09
     akhir
    0.09
     конце
    0.09
    Act Density 0.021%

    No Known Activations