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

    Neuronpedia

    INDEX
    Explanations

    work requiring understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    蓓
    0.50
    潑
    0.47
    開放
    0.45
    分鐘
    0.44
     respond
    0.42
     "";
    0.42
    ភា
    0.41
    Ꮡ
    0.41
     boardroom
    0.41
    បង្ហាញ
    0.41
    POSITIVE LOGITS
    arlo
    0.50
     ло
    0.45
    olio
    0.45
    osto
    0.43
    s
    0.43
     oltre
    0.42
     глу
    0.42
    стов
    0.41
     הע
    0.41
    zzle
    0.41
    Act Density 0.005%

    No Known Activations