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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grandson
    -0.07
     plaster
    -0.07
    -down
    -0.06
     granddaughter
    -0.06
     учнів
    -0.06
    _eq
    -0.06
    anto
    -0.06
    down
    -0.06
    occasion
    -0.06
     IMO
    -0.06
    POSITIVE LOGITS
    جز
    0.06
    句
    0.06
    ัญช
    0.06
    sume
    0.06
    .subplot
    0.06
     stockings
    0.06
    唱
    0.06
    shed
    0.06
     Sn
    0.06
     이용
    0.06
    Act Density 0.013%

    No Known Activations