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

    Neuronpedia

    INDEX
    Explanations

    immune

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Whitney
    -0.07
    ären
    -0.07
     ':
    -0.06
    WX
    -0.06
    transpose
    -0.06
     Wine
    -0.06
     هن
    -0.06
    ,W
    -0.06
     Bret
    -0.06
     debe
    -0.06
    POSITIVE LOGITS
    .hashCode
    0.07
    -dev
    0.06
    ''"
    0.06
    ีเม
    0.06
    易
    0.06
    Route
    0.06
    qq
    0.06
     covid
    0.06
     Laundry
    0.06
    ereum
    0.06
    Act Density 0.008%

    No Known Activations