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

    Neuronpedia

    INDEX
    Explanations

    language related to user interactions and feedback mechanisms in applications

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

    end of sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intptr
    -0.40
     ślub
    -0.37
     ilustracja
    -0.36
     investigação
    -0.34
    ecuzione
    -0.34
     announced
    -0.34
     asserted
    -0.34
    rosia
    -0.34
     Bescheid
    -0.34
     كورة
    -0.32
    POSITIVE LOGITS
     CreateTagHelper
    0.63
     MainAxisSize
    0.60
     désolés
    0.58
    tanleria
    0.56
    :✨
    0.55
    InitVars
    0.52
    $_['
    0.50
    Хьажоргаш
    0.49
     Numerade
    0.48
     resourceCulture
    0.47
    Act Density 0.066%

    No Known Activations