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

    Neuronpedia

    INDEX
    Explanations

    asking and answering questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ই
    0.46
    卻
    0.43
    ऎ
    0.42
    ison
    0.40
    GEN
    0.39
    却
    0.39
    gen
    0.39
    만
    0.39
    ение
    0.38
    卋
    0.38
    POSITIVE LOGITS
     BTW
    0.49
     annen
    0.43
     übrigens
    0.43
    BTW
    0.40
     btw
    0.39
     Other
    0.38
     Darüber
    0.38
     HttpSession
    0.38
    ሌ
    0.38
     inductive
    0.37
    Act Density 0.003%

    No Known Activations