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

    Neuronpedia

    INDEX
    Explanations

    do you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dislikes
    0.44
     দেখিতে
    0.43
    സ്
    0.41
    ской
    0.40
    arasi
    0.39
     pledges
    0.39
    σε
    0.38
    uthers
    0.38
     रिकार्ड
    0.38
     favors
    0.37
    POSITIVE LOGITS
     univerz
    0.49
     একটা
    0.46
     erzählt
    0.42
     لازم
    0.40
     duração
    0.40
     얘는
    0.40
     этому
    0.39
     tämä
    0.39
     century
    0.39
    這個
    0.38
    Act Density 0.002%

    No Known Activations