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

    Neuronpedia

    INDEX
    Explanations

    physical positions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recorr
    -0.08
     sínt
    -0.08
     subscribers
    -0.08
     Subscribers
    -0.08
     unsubscribe
    -0.07
    த்த
    -0.07
    规范
    -0.07
     PDFs
    -0.07
     deline
    -0.07
    涵
    -0.07
    POSITIVE LOGITS
     upright
    0.14
     Orientation
    0.11
     rotated
    0.11
     Upr
    0.11
     orientation
    0.11
    Orientation
    0.10
    orientation
    0.09
     sideways
    0.09
    _orientation
    0.09
     положении
    0.09
    Act Density 0.012%

    No Known Activations