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

    Neuronpedia

    INDEX
    Explanations

    authors in academic citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kiles
    0.38
    ⁈
    0.37
     darker
    0.37
    していて
    0.36
    ந்தை
    0.36
     CompoundButton
    0.36
     grayish
    0.36
     FirstName
    0.35
     Nether
    0.35
    ਊ
    0.35
    POSITIVE LOGITS
     et
    0.90
     eds
    0.58
     &
    0.50
    等人
    0.48
    etal
    0.47
     Jr
    0.45
     एट
    0.43
    ová
    0.41
     এট
    0.41
    Et
    0.39
    Act Density 0.006%

    No Known Activations