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

    Neuronpedia

    INDEX
    Explanations

    URLs and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    孛
    0.25
     아
    0.25
    𝗯
    0.25
    f
    0.24
    ர்
    0.24
    ৰ
    0.24
     linearized
    0.23
     বিষয়টা
    0.23
    ون
    0.22
    نا
    0.22
    POSITIVE LOGITS
    0.30
    ifi
    0.28
    н
    0.27
     n
    0.27
    ise
    0.27
    oda
    0.27
    unn
    0.26
    yl
    0.25
    ito
    0.25
    itate
    0.25
    Act Density 0.795%

    No Known Activations