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

    Neuronpedia

    INDEX
    Explanations

    counting from 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Whittaker
    0.43
    änn
    0.41
     Waik
    0.39
    endim
    0.39
     כמ
    0.38
    unächst
    0.38
     Wakefield
    0.38
     Neville
    0.37
     magicians
    0.37
    änt
    0.37
    POSITIVE LOGITS
    arly
    0.44
    chain
    0.41
    gz
    0.39
    cub
    0.38
    વાન
    0.38
    ความ
    0.38
    链
    0.38
    recognition
    0.38
     لاءِ
    0.37
    vide
    0.37
    Act Density 0.003%

    No Known Activations