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

    Neuronpedia

    INDEX
    Explanations

    light, sun, spiritual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     %
    0.43
     Pfizer
    0.39
     Multin
    0.38
     lib
    0.38
     Last
    0.38
    TreeNode
    0.38
     dernière
    0.37
     last
    0.37
     Punto
    0.37
    abet
    0.37
    POSITIVE LOGITS
     छेड़
    0.44
     образования
    0.41
    CycleOffset
    0.41
    Hozzáférés
    0.40
    effectiveness
    0.40
    鍰
    0.40
    马克
    0.39
     pendidikan
    0.38
     ஆட்ச
    0.38
    efficacité
    0.37
    Act Density 0.000%

    No Known Activations