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

    Neuronpedia

    INDEX
    Explanations

    This

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     championships
    -0.08
    .help
    -0.07
    ביע
    -0.07
    鳒
    -0.07
    utex
    -0.06
     Wikipedia
    -0.06
     explained
    -0.06
    cmp
    -0.06
     defines
    -0.06
     dương
    -0.06
    POSITIVE LOGITS
    _o
    0.07
    恶魔
    0.07
    icers
    0.07
    Gi
    0.07
     winding
    0.07
    دي
    0.06
    {o
    0.06
    帷
    0.06
    椟
    0.06
     moi
    0.06
    Act Density 0.007%

    No Known Activations