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

    Neuronpedia

    INDEX
    Explanations

    connection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    允许
    -0.07
    㬚
    -0.07
     vos
    -0.07
    atori
    -0.06
    委组织
    -0.06
    Bio
    -0.06
    Pok
    -0.06
     retarded
    -0.06
    (edit
    -0.06
     bảo
    -0.06
    POSITIVE LOGITS
    뒀
    0.08
    geführt
    0.07
     photographer
    0.07
    녔
    0.07
     üret
    0.07
    "])){↵
    0.07
    ㅜ
    0.07
     poet
    0.07
     nun
    0.07
    fout
    0.07
    Act Density 0.025%

    No Known Activations