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

    Neuronpedia

    INDEX
    Explanations

    property copyright

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    1.02
    www
    0.89
     (
    0.86
     Sex
    0.86
    ك
    0.85
    <strong>
    0.82
    <em>
    0.81
     M
    0.81
    ---
    0.80
    0
    0.79
    POSITIVE LOGITS
    THING
    0.90
    <unused15>
    0.89
     filePath
    0.89
    ReaderWriter
    0.89
     தீங்கு
    0.89
     vš
    0.87
    Mie
    0.87
     পাকিস্ত
    0.87
    ﺒ
    0.87
    inuous
    0.86
    Act Density 0.000%

    No Known Activations