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

    Neuronpedia

    INDEX
    Explanations

    marked or inscribed objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     davran
    0.78
    仹
    0.71
     outages
    0.70
     ciel
    0.70
     nieuws
    0.69
    仮想
    0.69
    LayoutStyle
    0.68
     त्रास
    0.67
     instances
    0.66
    引进
    0.66
    POSITIVE LOGITS
     engraved
    2.44
     inscription
    2.38
     inscribed
    2.27
     engraving
    2.18
     inscriptions
    2.17
     stamped
    2.04
     lettering
    1.98
     embossed
    1.96
     embl
    1.95
     engravings
    1.95
    Act Density 0.189%

    No Known Activations