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

    Neuronpedia

    INDEX
    Explanations

    greetings and farewell phrases

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

    code compounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <h2>
    -0.36
    maketitle
    -0.32
    <eos>
    -0.31
     sencilla
    -0.29
    kező
    -0.27
     asamblea
    -0.27
     pères
    -0.27
     Einfach
    -0.26
     Polsek
    -0.26
     alquiler
    -0.26
    POSITIVE LOGITS
     Paglinawan
    0.88
     Roskov
    0.82
     EconPapers
    0.81
    InjectAttribute
    0.78
    DockStyle
    0.78
     InputDecoration
    0.77
    StoryboardSegue
    0.75
     незавершена
    0.74
     للمعارف
    0.74
    AddTagHelper
    0.73
    Act Density 0.008%

    No Known Activations