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

    Neuronpedia

    INDEX
    Explanations

    transparency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _dummy
    -0.08
    Dummy
    -0.08
     Dummy
    -0.08
     ignore
    -0.07
    niejsze
    -0.07
     hardly
    -0.07
     replacement
    -0.07
     Toulouse
    -0.07
    Doctor
    -0.07
    ehir
    -0.07
    POSITIVE LOGITS
     openly
    0.14
     transparencia
    0.13
     transpar
    0.13
     Transparency
    0.13
     transparency
    0.13
    透明
    0.13
     Transpar
    0.13
     públic
    0.12
    Transparency
    0.11
     прозрач
    0.11
    Act Density 0.032%

    No Known Activations