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

    Neuronpedia

    INDEX
    Explanations

    XML tags and attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     एमबी
    0.45
     Phosph
    0.44
     doped
    0.43
     ViewModel
    0.42
     fancied
    0.42
     MoU
    0.42
     Footage
    0.41
     MSS
    0.41
     Fantasy
    0.40
     Phosphate
    0.40
    POSITIVE LOGITS
    ONLY
    0.37
    కర
    0.37
     declarative
    0.36
     informal
    0.35
     পুনর্ব
    0.35
    שורים
    0.34
    烯
    0.34
     đương
    0.33
    IFY
    0.33
    ববার
    0.33
    Act Density 0.000%

    No Known Activations