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

    Neuronpedia

    INDEX
    Explanations

    Division

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     induce
    -0.08
     Carpet
    -0.07
    LEE
    -0.07
     Parcel
    -0.06
    ลอง
    -0.06
    difference
    -0.06
    ocurrency
    -0.06
     Lunch
    -0.06
     contingency
    -0.06
    Indeed
    -0.06
    POSITIVE LOGITS
     значительно
    0.07
    SetName
    0.07
    权益
    0.07
    'utilisation
    0.07
    伐
    0.07
    新华社
    0.07
    カード
    0.07
     manual
    0.07
    玩耍
    0.07
    娘家
    0.07
    Act Density 0.000%

    No Known Activations