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

    Neuronpedia

    INDEX
    Explanations

    drainage features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    病情
    0.47
    राब
    0.45
    aceted
    0.45
    вом
    0.44
    increased
    0.43
    輸出
    0.43
    皮
    0.43
    ранд
    0.42
    零件
    0.42
    ក់
    0.41
    POSITIVE LOGITS
     Months
    0.53
     Jurassic
    0.50
     begin
    0.48
     Year
    0.48
     Salad
    0.47
     Johan
    0.47
     Easter
    0.46
     Genesis
    0.46
     Ep
    0.46
     Yang
    0.46
    Act Density 0.002%

    No Known Activations