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

    Neuronpedia

    INDEX
    Explanations

    TABLE

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rho
    -0.07
     Interior
    -0.07
     Halloween
    -0.07
    	style
    -0.07
    Pen
    -0.07
     painted
    -0.07
     notation
    -0.07
     scenarios
    -0.07
    sigma
    -0.07
     Thompson
    -0.06
    POSITIVE LOGITS
     -,
    0.07
     glide
    0.07
    151
    0.07
     `'
    0.06
    ROI
    0.06
    ักษณ
    0.06
    avern
    0.06
     sitios
    0.06
    �
    0.06
     Markus
    0.06
    Act Density 0.015%

    No Known Activations