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

    Neuronpedia

    INDEX
    Explanations

    sold separately

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ندر
    -0.07
     Bill
    -0.07
     TED
    -0.07
     trustee
    -0.06
     Else
    -0.06
     Uran
    -0.06
     là
    -0.06
     police
    -0.06
     Pizza
    -0.06
    /ubuntu
    -0.06
    POSITIVE LOGITS
     Patreon
    0.07
     breakup
    0.06
    express
    0.06
     tung
    0.06
     olay
    0.06
     ageing
    0.06
     ผล
    0.06
    BLE
    0.06
    YP
    0.06
    :false
    0.06
    Act Density 0.081%

    No Known Activations