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

    Neuronpedia

    INDEX
    Explanations

    vector magnitudes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rows
    -0.08
    談
    -0.08
    上
    -0.08
    �
    -0.08
    	rows
    -0.08
    頁
    -0.07
    .Rows
    -0.07
     events
    -0.07
    Rows
    -0.07
    男女
    -0.07
    POSITIVE LOGITS
    Magnitude
    0.10
     magnitude
    0.10
     donut
    0.09
     onzeker
    0.09
     magn
    0.09
     Magn
    0.08
    agnitude
    0.08
     Orang
    0.08
     Swing
    0.08
     swinger
    0.08
    Act Density 0.023%

    No Known Activations