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

    Neuronpedia

    INDEX
    Explanations

    references to sharing or including content, especially images and posts

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

    presenting or including something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WaitGroup
    -0.55
     nahilalakip
    -0.55
    Искәрмәләр
    -0.48
    ༘
    -0.45
     Wunder
    -0.44
     autorytatywna
    -0.43
    Rhestr
    -0.43
     Mur
    -0.43
    LVANIA
    -0.43
     Buff
    -0.43
    POSITIVE LOGITS
     NSCoder
    0.46
     voici
    0.45
     ComVisible
    0.41
     것입니다
    0.40
     Warszawie
    0.37
     publiée
    0.37
     metro
    0.36
     зді
    0.35
     universel
    0.35
     defaultstate
    0.35
    Act Density 0.110%

    No Known Activations