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

    Neuronpedia

    INDEX
    Explanations

    Comparisons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     UIButton
    -0.08
    圆形
    -0.07
    .dc
    -0.07
     GB
    -0.07
    去年
    -0.07
    埋
    -0.07
    不间
    -0.07
     jó
    -0.06
    方形
    -0.06
     Gel
    -0.06
    POSITIVE LOGITS
     payload
    0.08
    やら
    0.07
    輩
    0.07
    彀
    0.07
    感悟
    0.07
     Mesa
    0.07
    аг
    0.07
     Classes
    0.07
    cadena
    0.07
    적이
    0.06
    Act Density 0.049%

    No Known Activations