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

    Neuronpedia

    INDEX
    Explanations

    color, age, temperature

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     площадь
    0.84
     taille
    0.77
     fiyat
    0.76
     علاقے
    0.74
     tinha
    0.72
     बोझ
    0.72
    ിയുടെ
    0.72
    addObject
    0.71
    ถม
    0.70
     অংশে
    0.70
    POSITIVE LOGITS
     preference
    1.17
     preferences
    1.13
     selection
    1.01
     Preference
    0.98
    preference
    0.97
     designations
    0.97
     cues
    0.96
     appropriateness
    0.95
    别的
    0.95
     determination
    0.94
    Act Density 0.422%

    No Known Activations