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

    Neuronpedia

    INDEX
    Explanations

    underscore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    urga
    -0.07
    Options
    -0.07
    �乐
    -0.07
    овани
    -0.07
    بي
    -0.06
    -bs
    -0.06
    เวล
    -0.06
    .level
    -0.06
     gone
    -0.06
    Davis
    -0.06
    POSITIVE LOGITS
     bpy
    0.06
     预
    0.06
     plumber
    0.06
     resp
    0.06
     стол
    0.06
    _w
    0.06
     nominee
    0.06
     tah
    0.06
     execut
    0.06
     аналіз
    0.05
    Act Density 0.010%

    No Known Activations