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

    Neuronpedia

    INDEX
    Explanations

    float numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ವಿಶೇಷ
    0.46
    🦒
    0.39
     ডোজ
    0.38
     અનુસાર
    0.38
     निराश
    0.38
    と比較
    0.38
    Bracketing
    0.38
    TRIG
    0.38
    Twins
    0.38
    Lowest
    0.38
    POSITIVE LOGITS
    jpg
    0.46
     století
    0.46
     century
    0.45
     secolo
    0.42
     pain
    0.41
     soit
    0.40
    лови
    0.40
     parked
    0.40
     ding
    0.40
    exe
    0.40
    Act Density 0.013%

    No Known Activations