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

    Neuronpedia

    INDEX
    Explanations

    possessives and their associated nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Types
    0.37
    possibly
    0.35
     Possibly
    0.34
     posibles
    0.33
    不错的
    0.33
     forskellige
    0.33
    的一些
    0.33
    шем
    0.32
    Specific
    0.32
     을
    0.32
    POSITIVE LOGITS
     fingers
    0.51
     eyes
    0.45
    oretically
    0.43
     onus
    0.43
    意思是
    0.43
    目的是
    0.42
    性は
    0.41
     fingerprints
    0.39
     goal
    0.39
     문제는
    0.39
    Act Density 0.024%

    No Known Activations