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

    Neuronpedia

    INDEX
    Explanations

    has apologised, has been, have emerged

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gewesen
    0.26
     gehad
    0.22
     havde
    0.22
     geweest
    0.21
    았던
    0.20
     pouv
    0.20
     gehabt
    0.19
     utilisons
    0.19
     hadde
    0.19
     damal
    0.19
    POSITIVE LOGITS
     recently
    0.21
    recently
    0.21
    kafka
    0.20
     ইতোমধ্যে
    0.20
     natomiast
    0.20
    inescence
    0.19
    近年
    0.19
     inzwischen
    0.19
     ইতিমধ্যেই
    0.19
    hta
    0.19
    Act Density 0.011%

    No Known Activations