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

    Neuronpedia

    INDEX
    Explanations

    programming questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ALERT
    -0.08
    URING
    -0.08
     إطار
    -0.07
     Marvel
    -0.07
    硫酸
    -0.07
    蘭
    -0.06
    .mybatis
    -0.06
    ụ
    -0.06
    锻
    -0.06
    璐
    -0.06
    POSITIVE LOGITS
    Ջ
    0.07
    稀
    0.07
    coc
    0.07
     Fay
    0.07
    څ
    0.07
     district
    0.07
    】
    0.07
     discrim
    0.06
     nich
    0.06
    ся
    0.06
    Act Density 0.043%

    No Known Activations