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

    Neuronpedia

    INDEX
    Explanations

    multiple languages "or"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     காலம்
    0.47
    ക്കണം
    0.43
     Diversity
    0.43
     Lecture
    0.43
     ساله
    0.43
     temperatur
    0.43
     rotting
    0.41
     Magazine
    0.41
     meagre
    0.41
     Geographic
    0.41
    POSITIVE LOGITS
    或者
    0.57
     또는
    0.50
    ión
    0.46
     arba
    0.46
    配送
    0.46
    或
    0.46
     અથવા
    0.45
     或者
    0.45
     оформления
    0.45
     або
    0.45
    Act Density 0.007%

    No Known Activations