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

    Neuronpedia

    INDEX
    Explanations

    In

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rying
    -0.07
    adopt
    -0.07
    .ColumnHeadersHeightSizeMode
    -0.07
    dept
    -0.06
     geil
    -0.06
    �
    -0.06
     forensic
    -0.06
    ?></
    -0.06
     joystick
    -0.06
     послед
    -0.06
    POSITIVE LOGITS
    /io
    0.07
    (filtered
    0.07
     airplanes
    0.07
    祝
    0.06
     setBackground
    0.06
    ’app
    0.06
     uncertainty
    0.06
     regards
    0.06
    /music
    0.06
    .future
    0.06
    Act Density 0.028%

    No Known Activations