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

    Neuronpedia

    INDEX
    Explanations

    explains why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     จึง
    0.38
    因而
    0.37
     pertanto
    0.37
     eruptions
    0.36
     sucrose
    0.34
     Consequently
    0.33
     Its
    0.33
    ąc
    0.33
     발생
    0.32
     malignancies
    0.32
    POSITIVE LOGITS
    为什么
    0.56
     why
    0.53
     warum
    0.49
     kenapa
    0.48
    why
    0.45
     explained
    0.44
     reasons
    0.44
    おすすめ
    0.43
    為什麼
    0.43
     waarom
    0.43
    Act Density 0.321%

    No Known Activations