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

    Neuronpedia

    INDEX
    Explanations

    importance and purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Diese
    0.15
     glycolysis
    0.15
     \
    0.15
     '',
    0.15
     antique
    0.14
     scrotum
    0.14
     Ait
    0.14
     Apollo
    0.14
     rì
    0.14
     ',
    0.13
    POSITIVE LOGITS
     for
    0.31
    पणे
    0.27
     для
    0.26
     untuk
    0.24
    для
    0.24
     pentru
    0.24
     برای
    0.24
     bagi
    0.23
     για
    0.22
     banget
    0.22
    Act Density 2.926%

    No Known Activations