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

    Neuronpedia

    INDEX
    Explanations

    challenges and limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     เลือก
    0.44
     ausgezeichnet
    0.44
    挑选
    0.44
     Boż
    0.42
     بو
    0.40
     선정
    0.38
     크
    0.38
     سلس
    0.38
     选择
    0.38
    Creation
    0.37
    POSITIVE LOGITS
     unsatisfactory
    0.77
     inadequate
    0.74
    unfortunately
    0.73
     unfortunately
    0.71
     insufficient
    0.70
     inadequ
    0.70
     insuficiente
    0.70
    Unfortunately
    0.68
     inadequacy
    0.67
    現状
    0.66
    Act Density 0.071%

    No Known Activations