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

    Neuronpedia

    INDEX
    Explanations

    `明日`, `smile`, `bright`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    आम
    0.40
     adı
    0.39
    Packing
    0.39
    啇
    0.38
    剤
    0.37
    ဆက်
    0.37
    çi
    0.37
     अधिक
    0.36
    嚴
    0.36
     असल
    0.36
    POSITIVE LOGITS
     Nath
    0.47
    ataires
    0.42
    ნება
    0.40
     Napa
    0.39
     Petra
    0.39
     Kindly
    0.37
     Samantha
    0.37
     Π
    0.36
     хода
    0.36
     stretchy
    0.36
    Act Density 0.000%

    No Known Activations