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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.59
     animaux
    0.49
     s
    0.46
     dart
    0.46
     nightmares
    0.46
     jinak
    0.45
     irritating
    0.44
     eine
    0.44
     monitor
    0.42
     annoying
    0.42
    POSITIVE LOGITS
     sincer
    0.68
    слен
    0.64
     কৃতজ্ঞ
    0.64
     всех
    0.63
    祝福
    0.63
     तहे
    0.62
     आशीष
    0.61
    すべての
    0.60
     جميع
    0.59
     всіх
    0.59
    Act Density 0.009%

    No Known Activations