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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and logarithms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Teddy
    0.47
    לי
    0.43
    ບໍ
    0.39
     ब्यूरो
    0.38
    㞔
    0.38
    אה
    0.38
     Teddy
    0.37
    uirre
    0.37
    Johnny
    0.37
    มั่น
    0.36
    POSITIVE LOGITS
     $(
    0.44
     [(
    0.43
     nonzero
    0.42
     {\
    0.41
     (),
    0.41
     parallelogram
    0.41
     ().
    0.40
     equation
    0.40
     {
    0.40
     $$\
    0.40
    Act Density 0.019%

    No Known Activations