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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     op
    -0.07
     Wolfe
    -0.07
     diesem
    -0.07
    outes
    -0.07
    ﺪ
    -0.07
     Kirby
    -0.07
     Joyce
    -0.07
    偵
    -0.06
     Davidson
    -0.06
    -scripts
    -0.06
    POSITIVE LOGITS
    좋
    0.07
     fart
    0.07
    .hasNext
    0.07
    搞
    0.07
    ",@"
    0.06
    몫
    0.06
    整改措施
    0.06
    牢牢
    0.06
    .moveToNext
    0.06
     Aging
    0.06
    Act Density 0.035%

    No Known Activations