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

    Neuronpedia

    INDEX
    Explanations

    code snippets and file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rüstung
    0.38
    ToPlot
    0.37
    ゥム
    0.37
    溆
    0.36
    ূনতম
    0.36
    OfDeath
    0.36
    лянчук
    0.36
    狎
    0.36
    FromFile
    0.36
    ীত
    0.35
    POSITIVE LOGITS
    6
    0.34
    has
    0.34
    7
    0.34
     d
    0.34
    2
    0.34
    9
    0.33
    '
    0.33
     has
    0.33
    0
    0.32
    5
    0.31
    Act Density 0.171%

    No Known Activations