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

    Neuronpedia

    INDEX
    Explanations

    Math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     σε
    -0.07
     kend
    -0.07
     A
    -0.06
    -corner
    -0.06
    了一
    -0.06
    _meas
    -0.06
    我
    -0.06
     ye
    -0.06
     م
    -0.06
    'app
    -0.06
    POSITIVE LOGITS
     Marino
    0.07
    middlewares
    0.06
     Farage
    0.06
    .It
    0.06
     handwritten
    0.06
     trụ
    0.06
    .lineTo
    0.06
     BufferedImage
    0.06
    apons
    0.06
    .Val
    0.06
    Act Density 0.031%

    No Known Activations