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

    Neuronpedia

    INDEX
    Explanations

    become more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ниво
    0.44
    rawal
    0.42
     Stav
    0.42
    ahun
    0.42
     мар
    0.41
    йон
    0.39
    ដ្ឋាន
    0.38
     fraudulently
    0.38
     lograr
    0.37
    udal
    0.37
    POSITIVE LOGITS
     guiding
    0.40
     اظہار
    0.39
     voice
    0.39
     যাঁ
    0.38
    也将
    0.38
    聲音
    0.38
    दे
    0.38
     someday
    0.38
     helping
    0.37
     voices
    0.36
    Act Density 0.006%

    No Known Activations