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

    Neuronpedia

    INDEX
    Explanations

    periods of time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     drawRight
    0.41
    weathermap
    0.38
    perror
    0.37
     layi
    0.36
     offender
    0.36
    pulsewidth
    0.36
    udarstvennyj
    0.35
    deoxy
    0.35
     katk
    0.34
     ক্ষত্রিয়
    0.34
    POSITIVE LOGITS
     Transfers
    0.39
     خیال
    0.37
     Transfer
    0.37
    𝐟
    0.37
    Transfer
    0.35
    ế
    0.35
    𝒇
    0.35
    電力
    0.35
     זמן
    0.34
    ्यता
    0.34
    Act Density 0.000%

    No Known Activations