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

    Neuronpedia

    INDEX
    Explanations

    boolean type declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    at
    1.41
    ת
    1.33
    d
    1.29
    ا
    1.28
    ্ড
    1.24
    我认为
    1.21
    xiv
    1.17
    みました
    1.16
    an
    1.14
    होम
    1.12
    POSITIVE LOGITS
     fact
    1.18
     sejarah
    1.17
    vorm
    1.12
    creen
    1.12
    PerformLayout
    1.08
    ುದು
    1.07
    gebäude
    1.06
     lack
    1.05
    šu
    1.05
     promen
    1.04
    Act Density 0.095%

    No Known Activations