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

    Neuronpedia

    INDEX
    Explanations

    common words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.73
    ValueStyle
    -0.62
    cshtml
    -0.61
    MemoryWarning
    -0.59
    idate
    -0.58
     Himo
    -0.57
    letoe
    -0.54
    ondissement
    -0.54
    setVerticalGroup
    -0.54
    tonsoft
    -0.54
    POSITIVE LOGITS
    <bos>
    1.39
    ↵↵
    0.57
    Made
    0.50
     with
    0.49
     blanches
    0.48
     Made
    0.48
     the
    0.48
     not
    0.47
    The
    0.47
     rembour
    0.45
    Act Density 0.016%

    No Known Activations