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

    Neuronpedia

    INDEX
    Explanations

    code structure and programming elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ➲
    0.32
    豕
    0.31
    ⚉
    0.29
    Flying
    0.28
    پا
    0.28
    悅
    0.28
    Lambda
    0.28
     ஆகிய
    0.28
    ей
    0.27
     prema
    0.27
    POSITIVE LOGITS
     recalls
    0.29
     ncols
    0.29
     vs
    0.29
    ``
    0.27
     estr
    0.27
     emph
    0.27
     covid
    0.27
     transcripts
    0.27
     instagram
    0.26
     testAvg
    0.26
    Act Density 0.054%

    No Known Activations