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

    Neuronpedia

    INDEX
    Explanations

    Who

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .hwp
    -0.06
     ("
    -0.06
    有关
    -0.06
     EOS
    -0.06
    startdate
    -0.06
    %d
    -0.06
     لك
    -0.06
     kd
    -0.06
    -years
    -0.06
    ivan
    -0.06
    POSITIVE LOGITS
    柜
    0.08
     ऑ
    0.07
    젤
    0.07
    mie
    0.07
     Clan
    0.07
     tags
    0.07
    oxy
    0.06
    casecmp
    0.06
     IOException
    0.06
     --------------------
    0.06
    Act Density 0.008%

    No Known Activations