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

    Neuronpedia

    INDEX
    Explanations

    terms related to extensions and their variations in context

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

    "Ext" followed by other characters

    np_acts-logits-general · gemini-2.0-flash

    extend and extension

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PullParser
    -0.80
    __':
    -0.79
    PMailer
    -0.75
     للمعارف
    -0.75
     CreateTagHelper
    -0.75
     nakalista
    -0.70
     الحره
    -0.69
    gdx
    -0.67
    urlpatterns
    -0.65
    脚注の使い方
    -0.64
    POSITIVE LOGITS
    Extended
    0.89
    extended
    0.87
     extensions
    0.87
     Extend
    0.85
     Extension
    0.85
     exten
    0.85
     extend
    0.84
     Ext
    0.83
     extending
    0.83
     EXT
    0.82
    Act Density 0.090%

    No Known Activations