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

    Neuronpedia

    INDEX
    Explanations

    grammar and language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     фармацев
    0.44
     आक्रोश
    0.44
     драй
    0.43
    িয়
    0.42
     ड्रोन
    0.41
    ᑐ
    0.41
     émotion
    0.41
     dialing
    0.40
     منسل
    0.40
     гара
    0.40
    POSITIVE LOGITS
     English
    0.47
    grammar
    0.44
     As
    0.43
     wichtig
    0.43
     George
    0.42
     Sometimes
    0.42
     Both
    0.41
     je
    0.41
     wichtigen
    0.41
     Spelling
    0.41
    Act Density 0.011%

    No Known Activations