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

    Neuronpedia

    INDEX
    Explanations

    scroll down to find option

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Blurred
    0.50
     обеспечивает
    0.48
    Empty
    0.45
     обеспечи
    0.45
    че
    0.44
    Celebr
    0.44
    Providing
    0.44
    י
    0.43
     cardiomyocyte
    0.42
     poskyt
    0.42
    POSITIVE LOGITS
     frog
    0.42
    兇
    0.38
     brunes
    0.37
     logically
    0.37
    驟
    0.36
     thêm
    0.36
    sby
    0.36
     anot
    0.34
     карда
    0.34
     adjust
    0.34
    Act Density 0.012%

    No Known Activations