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

    Neuronpedia

    INDEX
    Explanations

    models

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    人生
    -0.08
     chất
    -0.07
    宠
    -0.07
     pacientes
    -0.07
     nghĩa
    -0.07
     dưỡng
    -0.07
    رضى
    -0.07
    forgettable
    -0.07
    京东
    -0.07
     Danger
    -0.07
    POSITIVE LOGITS
     Kore
    0.07
     Liên
    0.07
     SES
    0.07
     Elo
    0.07
    mel
    0.07
    NU
    0.07
     Blo
    0.07
     She
    0.06
    .')
    0.06
     Ahmed
    0.06
    Act Density 0.002%

    No Known Activations