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

    Neuronpedia

    INDEX
    Explanations

    positive affirmations and praise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     इजीली
    0.80
    迅
    0.75
     suitably
    0.72
     facilmente
    0.70
     sufficiently
    0.69
     facilement
    0.69
     Accordingly
    0.68
     seguito
    0.67
     Towards
    0.67
    仨
    0.67
    POSITIVE LOGITS
     иметь
    1.26
     having
    1.13
     imati
    1.02
     knowing
    1.00
    having
    0.97
    Having
    0.96
     знать
    0.88
     noting
    0.88
    knowing
    0.87
     мати
    0.87
    Act Density 0.113%

    No Known Activations