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

    Neuronpedia

    INDEX
    Explanations

    material product origin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Edelstahl
    0.89
    HTML
    0.86
    機能
    0.86
     HTML
    0.85
     polyethylene
    0.83
     сили
    0.83
     lucr
    0.82
    XML
    0.80
     tevé
    0.80
     funktion
    0.80
    POSITIVE LOGITS
    製の
    1.60
    制品
    1.25
    製
    1.23
    ாலான
    1.17
    質の
    1.07
    ிலான
    1.03
     изделия
    1.00
     आधारित
    0.95
     издели
    0.94
    áce
    0.94
    Act Density 0.329%

    No Known Activations