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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    司
    -0.07
     mv
    -0.06
     Hell
    -0.06
    Ý
    -0.06
    酒
    -0.06
     balık
    -0.06
    루
    -0.06
    cales
    -0.06
     tempered
    -0.06
     Reynolds
    -0.06
    POSITIVE LOGITS
    이를
    0.06
    /Sh
    0.06
    .Th
    0.06
    Κ
    0.06
     td
    0.06
    }}</
    0.06
    ↵        ↵        ↵
    0.06
    rafted
    0.06
    resh
    0.05
    ，↵
    0.05
    Act Density 0.093%

    No Known Activations