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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     laundry
    -0.06
    Schedulers
    -0.06
    Dual
    -0.06
     sushi
    -0.06
     Diseases
    -0.06
     Tess
    -0.06
     middleware
    -0.06
    Taking
    -0.06
     бор
    -0.06
    binations
    -0.06
    POSITIVE LOGITS
    [class
    0.06
    APE
    0.06
    .XML
    0.06
    \Auth
    0.06
     heute
    0.06
     pad
    0.06
    ้าของ
    0.06
     rib
    0.06
     adres
    0.06
    ==$
    0.06
    Act Density 0.039%

    No Known Activations