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

    Neuronpedia

    INDEX
    Explanations

    layout and sizing parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     හ
    0.44
    Mare
    0.40
     genommen
    0.39
     cleansed
    0.38
    gebaut
    0.37
     build
    0.37
    虹
    0.37
    驯
    0.37
     dibangun
    0.37
     Molina
    0.36
    POSITIVE LOGITS
    textwidth
    0.59
    columnwidth
    0.52
     margins
    0.51
    footnotes
    0.51
    oddsidemargin
    0.46
    margins
    0.45
     hsize
    0.44
    Margin
    0.43
    Margins
    0.43
     margin
    0.42
    Act Density 0.001%

    No Known Activations