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

    Neuronpedia

    INDEX
    Explanations

    references to programming constructs related to widgets and generated methods in code

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

    layout weight and widget

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dessus
    -0.36
     चीज़ों
    -0.36
     régimen
    -0.35
    |'
    -0.34
     éxitos
    -0.34
    SOUNDBITE
    -0.33
    TypedDataSet
    -0.33
     éste
    -0.33
    habitude
    -0.33
     règne
    -0.32
    POSITIVE LOGITS
    annotation
    1.50
     annotation
    0.91
    RequestMapping
    0.85
    annotate
    0.79
     Annotation
    0.79
    HtmlAttribute
    0.78
    SpringBootTest
    0.76
    RestController
    0.75
    ArgumentParser
    0.73
    annot
    0.73
    Act Density 0.001%

    No Known Activations