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

    Neuronpedia

    INDEX
    Explanations

    closing braces and other syntactical elements in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets (C#, XAML)

    np_acts-logits-general · gemini-2.0-flash

    C# code and error messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CloseOperation
    -0.63
     {}));
    -0.62
    __':
    -0.61
     Nosotros
    -0.60
    ListItemIcon
    -0.59
    []){
    -0.58
    praš
    -0.58
    "><?=
    -0.57
     împre
    -0.57
     decât
    -0.56
    POSITIVE LOGITS
    ($"
    0.62
    ($"{
    0.60
    altham
    0.59
     cref
    0.56
     ref
    0.51
    HEAST
    0.50
    roskop
    0.50
    WriteLine
    0.50
    icycle
    0.47
     $"{
    0.47
    Act Density 0.029%

    No Known Activations