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

    Neuronpedia

    INDEX
    Explanations

    why is or that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     داعش
    0.34
    ধানা
    0.33
    ޏ
    0.32
    тивний
    0.31
    欴
    0.30
    ಪ
    0.30
    ད
    0.30
     ediyor
    0.29
     independents
    0.29
    સ્થા
    0.29
    POSITIVE LOGITS
    ⁤
    0.35
    ____
    0.33
     일반적으로
    0.33
     '',
    0.32
     ಸಾಮಾನ್ಯವಾಗಿ
    0.32
    ⁢
    0.31
     remarkable
    0.31
     ).
    0.31
     fundamentally
    0.31
     ….
    0.31
    Act Density 0.329%

    No Known Activations