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

    Neuronpedia

    INDEX
    Explanations

    Quebec

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _buf
    -0.08
     shutter
    -0.06
    -volume
    -0.06
    Ross
    -0.06
    θυ
    -0.06
     Wolver
    -0.06
     deceive
    -0.06
     derivative
    -0.06
    ■■
    -0.06
     device
    -0.06
    POSITIVE LOGITS
     Quebec
    0.10
     Québec
    0.08
     tournaments
    0.07
     Montreal
    0.07
    outines
    0.07
    ifiant
    0.07
     dopo
    0.07
    tréal
    0.06
    mits
    0.06
     hikes
    0.06
    Act Density 0.008%

    No Known Activations