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

    Neuronpedia

    INDEX
    Explanations

    being acted upon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tört
    0.24
     fez
    0.23
    -(-
    0.23
    ഹി
    0.23
    իր
    0.22
    Lä
    0.22
     breaths
    0.22
     quitter
    0.22
    أ
    0.22
     mwen
    0.21
    POSITIVE LOGITS
     replaced
    0.31
     kept
    0.31
     approached
    0.30
     used
    0.30
     taken
    0.30
     evaluated
    0.29
     assessed
    0.29
     put
    0.29
     exploited
    0.29
     analysed
    0.29
    Act Density 0.420%

    No Known Activations