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

    Neuronpedia

    INDEX
    Explanations

    instances of Java class definitions and their associated methods

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

    constructors with parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ResponseWriter
    -0.50
    routeProvider
    -0.49
    ModelAdmin
    -0.45
     @"/
    -0.41
     virš
    -0.38
     resourceCulture
    -0.36
    SceneManagement
    -0.35
    parsedMessage
    -0.34
     tartalomajánló
    -0.34
    rzost
    -0.34
    POSITIVE LOGITS
     المعيارى
    0.65
     transfieras
    0.61
     Dad
    0.50
    fossil
    0.50
    talent
    0.49
     dad
    0.48
    gift
    0.48
     Eager
    0.48
     Bücher
    0.48
     Natives
    0.48
    Act Density 0.001%

    No Known Activations