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

    Neuronpedia

    INDEX
    Explanations

    Role-playing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vert
    -0.08
     TE
    -0.07
     Born
    -0.07
     matte
    -0.07
     질문
    -0.07
    ्षण
    -0.07
     eth
    -0.06
     цен
    -0.06
     thread
    -0.06
     seal
    -0.06
    POSITIVE LOGITS
     resides
    0.06
     объяс
    0.06
    .IsMatch
    0.06
    Tanggal
    0.06
    .**************↵
    0.06
     síd
    0.06
     التص
    0.06
    ,file
    0.06
    -wh
    0.06
    "—
    0.05
    Act Density 0.081%

    No Known Activations