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

    Neuronpedia

    INDEX
    Explanations

    invent facts or citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.48
    ి
    0.45
     Agile
    0.45
     Ч
    0.43
    passen
    0.43
    peasants
    0.43
    ي
    0.43
     До
    0.43
     Puppy
    0.42
    【
    0.42
    POSITIVE LOGITS
     Bisby
    0.49
    亘
    0.46
     veditabbo
    0.45
     biota
    0.43
     đợi
    0.43
     veget
    0.42
     inputArray
    0.41
    ভোগ
    0.41
     জীববিজ্ঞান
    0.41
     vegetarian
    0.40
    Act Density 0.001%

    No Known Activations