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

    Neuronpedia

    INDEX
    Explanations

    PowerPoint shapes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ാവ
    0.42
    Immediately
    0.42
     immédiatement
    0.41
    洺
    0.40
    ্রান্ত
    0.40
     ruimte
    0.39
     пространства
    0.39
    icch
    0.38
    さまざまな
    0.38
     회사
    0.38
    POSITIVE LOGITS
     shape
    0.46
     STEP
    0.44
     شكل
    0.41
     Shape
    0.41
    iscale
    0.40
    organ
    0.39
     гре
    0.39
    leden
    0.38
     MC
    0.38
    shape
    0.38
    Act Density 0.000%

    No Known Activations