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

    Neuronpedia

    INDEX
    Explanations

    maximum values and limits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     DELL
    0.42
     Maler
    0.40
    риб
    0.40
     Aver
    0.39
     AVER
    0.39
    េរ
    0.37
     horrible
    0.36
     Artes
    0.36
     Dell
    0.36
     AVG
    0.36
    POSITIVE LOGITS
     maximum
    1.41
    Maximum
    1.34
    最大
    1.30
    maximum
    1.30
     최대
    1.30
     अधिकतम
    1.24
     максимум
    1.22
     Maximum
    1.20
    max
    1.19
     максима
    1.19
    Act Density 0.050%

    No Known Activations