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

    Neuronpedia

    INDEX
    Explanations

    rack

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     오늘
    -0.07
     stolen
    -0.07
     Bray
    -0.06
     nearer
    -0.06
     Analy
    -0.06
    plants
    -0.06
     Dez
    -0.06
     obey
    -0.06
     gave
    -0.06
     Cp
    -0.06
    POSITIVE LOGITS
     Mandarin
    0.07
    #w
    0.07
    블
    0.07
     cabe
    0.06
    ข
    0.06
     nếu
    0.06
     _,
    0.06
     Unless
    0.06
    @Override
    0.06
     horm
    0.06
    Act Density 0.001%

    No Known Activations