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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    无形
    -0.07
    😀
    -0.07
    �
    -0.07
    屯
    -0.07
    翮
    -0.07
    -abs
    -0.06
     Beh
    -0.06
     StringTokenizer
    -0.06
    ="">
    -0.06
     hs
    -0.06
    POSITIVE LOGITS
     instance
    0.07
     interceptor
    0.07
    _APPLICATION
    0.07
     vtk
    0.07
    казывает
    0.06
     элемент
    0.06
    рыв
    0.06
    iling
    0.06
    (mark
    0.06
    .instances
    0.06
    Act Density 0.002%

    No Known Activations