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

    Neuronpedia

    INDEX
    Explanations

    phrases related to reduction and simplification in various contexts

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

    reduced to basics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     חיצוניים
    -0.59
    AsUp
    -0.54
     CreateTagHelper
    -0.53
    MLLoader
    -0.53
    HtmlAttribute
    -0.53
     समीक्षाओं
    -0.52
     encre
    -0.52
    findpost
    -0.51
    IBOutlet
    -0.50
     udaler
    -0.49
    POSITIVE LOGITS
     reduced
    0.60
     reducido
    0.57
     reducir
    0.52
     réduite
    0.52
    reduced
    0.52
     reduz
    0.51
     reduction
    0.50
     Reduced
    0.47
     reducción
    0.46
     REDUC
    0.46
    Act Density 0.047%

    No Known Activations