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

    Neuronpedia

    INDEX
    Explanations

    solving problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Референ
    0.36
    icits
    0.35
    thati
    0.34
    골
    0.33
    ptuous
    0.32
     പൂ
    0.32
    াত্র
    0.31
    azas
    0.31
     გამოი
    0.31
     புதி
    0.31
    POSITIVE LOGITS
     remedy
    2.39
    解决
    2.27
     mengatasi
    2.23
     remedied
    2.22
     remed
    2.19
     addressing
    2.17
     해결
    2.17
    解決
    2.13
     remedies
    2.11
     Addressing
    2.09
    Act Density 0.179%

    No Known Activations