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

    Neuronpedia

    INDEX
    Explanations

    symbols/punctuation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .”)
    0.51
     javascript
    0.49
     JavaScript
    0.48
     一般
    0.47
    ”).
    0.46
     Javascript
    0.45
    ’.”
    0.45
     XPath
    0.45
     Year
    0.44
     VIII
    0.43
    POSITIVE LOGITS
    "
    0.71
    "${
    0.64
    "_
    0.64
    "[
    0.61
    for
    0.60
    "$
    0.59
    "*
    0.59
    "\
    0.58
    "",
    0.58
    ["
    0.57
    Act Density 0.005%

    No Known Activations