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

    Neuronpedia

    INDEX
    Explanations

    May date

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     last
    0.37
     Last
    0.34
     allowing
    0.32
     Allowing
    0.32
    Last
    0.31
     அன்று
    0.31
    ultima
    0.30
     younger
    0.30
     vorige
    0.30
     knowing
    0.30
    POSITIVE LOGITS
    ÁN
    0.33
     ایرانی
    0.31
     मोहम्मद
    0.30
     ישראל
    0.30
    ARAJ
    0.30
    nić
    0.30
     ವರ್ಷ
    0.30
     মোহাম্মদ
    0.30
     حسين
    0.29
    Senha
    0.29
    Act Density 0.004%

    No Known Activations