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

    Neuronpedia

    INDEX
    Explanations

    foreign or code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Erie
    0.46
    \
    0.46
     Burgen
    0.45
     Vater
    0.44
     Henson
    0.43
    o
    0.42
     McInt
    0.42
    0.42
     ITV
    0.42
     jefe
    0.42
    POSITIVE LOGITS
    дування
    0.50
    <0x80>
    0.50
     vestiges
    0.47
    σου
    0.47
    િ
    0.47
    ਾਈ
    0.46
    க்கால்
    0.46
    πι
    0.46
    ്
    0.45
     alınd
    0.45
    Act Density 0.021%

    No Known Activations