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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and operations

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

    arithmetic calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.65
     Chwiliwch
    -0.62
     noDo
    -0.60
     Administrativna
    -0.56
     désolés
    -0.52
     للمعارف
    -0.51
     Exacts
    -0.50
     ujednoznacz
    -0.49
    翻攝
    -0.48
    RenderAtEndOf
    -0.47
    POSITIVE LOGITS
     GenerationType
    0.38
    idol
    0.37
     cotone
    0.36
    jsonwebtoken
    0.35
     INI
    0.35
    dep
    0.34
    ini
    0.34
     Levine
    0.33
     pymysql
    0.33
     olmayan
    0.33
    Act Density 0.296%

    No Known Activations