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

    Neuronpedia

    INDEX
    Explanations

    routes and methods

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .GetAxis
    -0.07
     flex
    -0.07
     thuật
    -0.07
    imuth
    -0.07
     antes
    -0.07
    urgical
    -0.06
    哚
    -0.06
    .est
    -0.06
    Vel
    -0.06
    想象力
    -0.06
    POSITIVE LOGITS
    برشلون
    0.06
    船上
    0.06
     attacking
    0.06
     Daniels
    0.06
    �
    0.06
    ԑ
    0.06
    تنسي
    0.06
     sıc
    0.06
    ˟
    0.06
    מדינ
    0.06
    Act Density 0.001%

    No Known Activations