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

    Neuronpedia

    INDEX
    Explanations

    bolded titles or code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     embargo
    0.34
     những
    0.32
     those
    0.30
     coloro
    0.29
     dals
    0.28
     infest
    0.28
     cabaret
    0.28
     bungalows
    0.28
     wok
    0.28
     تلك
    0.27
    POSITIVE LOGITS
    ิ
    0.33
    ํ
    0.33
     ሁለት
    0.32
    ucapkan
    0.31
    utation
    0.31
     는
    0.31
    ป็น
    0.31
    ål
    0.30
     =
    0.30
    }=
    0.29
    Act Density 0.911%

    No Known Activations