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

    Neuronpedia

    INDEX
    Explanations

    full

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alan
    -0.07
    ayım
    -0.07
    理
    -0.07
    REE
    -0.07
    ż
    -0.07
    /{{
    -0.06
     투
    -0.06
    %
    -0.06
    foto
    -0.06
    овани
    -0.06
    POSITIVE LOGITS
     sophisticated
    0.07
    kil
    0.07
     thorough
    0.06
    /bootstrap
    0.06
     Vehicles
    0.06
    |)↵
    0.06
     felony
    0.06
     Classical
    0.06
    ecedor
    0.06
    semble
    0.06
    Act Density 0.017%

    No Known Activations