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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cube
    -0.07
    ScreenWidth
    -0.07
    려요
    -0.06
     underrated
    -0.06
     поверхность
    -0.06
    rapid
    -0.06
     slew
    -0.06
     чис
    -0.06
    .Framework
    -0.06
     دخ
    -0.06
    POSITIVE LOGITS
     distress
    0.07
     GST
    0.07
     BW
    0.07
    .any
    0.06
     CONCAT
    0.06
    Leave
    0.06
     Mitt
    0.06
    ě
    0.06
    _PORT
    0.06
    ैल
    0.06
    Act Density 0.000%

    No Known Activations