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

    Neuronpedia

    INDEX
    Explanations

    opponent horizontally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wsz
    0.51
    ‒
    0.51
     onTap
    0.49
     Thoreau
    0.47
     publicit
    0.46
     AutoCAD
    0.46
     thiệu
    0.46
     Hadoop
    0.46
     arxiv
    0.45
     OCLC
    0.44
    POSITIVE LOGITS
     heavenly
    0.42
     bird
    0.41
     certain
    0.40
     triumph
    0.39
    צו
    0.37
     dip
    0.37
     cak
    0.36
     জিনিসের
    0.36
    Heaven
    0.36
     измене
    0.36
    Act Density 0.006%

    No Known Activations