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

    Neuronpedia

    INDEX
    Explanations

    numbers with units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    丵
    0.20
     Runnable
    0.18
     Cálculo
    0.18
     Prinzip
    0.18
     Algorithms
    0.18
     Bevölkerung
    0.18
     ദൈ
    0.18
     Jdbc
    0.18
     Civilization
    0.18
     இங்கு
    0.17
    POSITIVE LOGITS
    7
    0.27
    5
    0.24
    8
    0.23
    4
    0.23
    6
    0.23
    www
    0.22
    3
    0.22
    to
    0.22
    2
    0.22
     approximately
    0.22
    Act Density 0.877%

    No Known Activations