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

    Neuronpedia

    INDEX
    Explanations

    Supreme Court

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     adjustments
    0.44
     dresses
    0.44
    uciones
    0.44
    uin
    0.44
    essori
    0.43
     introductions
    0.42
     circuits
    0.41
     additives
    0.41
     anschließend
    0.41
    បង្ហ
    0.41
    POSITIVE LOGITS
    > </
    0.47
    </
    0.46
     }^{
    0.44
    ه‌ای
    0.43
    または
    0.42
    tela
    0.42
    娯
    0.42
    Nit
    0.42
    倉庫
    0.42
    ਠ
    0.42
    Act Density 0.001%

    No Known Activations