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

    Neuronpedia

    INDEX
    Explanations

    previous step

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ம்பு
    0.40
     Original
    0.39
     diaphragm
    0.39
     originality
    0.39
    سپ
    0.39
     minister
    0.38
    })$;
    0.38
     Mastery
    0.38
    қан
    0.37
    άσ
    0.37
    POSITIVE LOGITS
    sometimes
    0.43
     بالإضافة
    0.40
     راحت
    0.40
    也可以
    0.39
     गोइंग
    0.38
     TOOLS
    0.38
     ভূ
    0.37
     ইউনিভার
    0.37
    食事
    0.36
    soap
    0.36
    Act Density 0.000%

    No Known Activations