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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and expressions involving variables and operations

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

    solving for variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    explique
    -0.33
     copy
    -0.33
    θεν
    -0.32
    zczy
    -0.31
    әрмәләр
    -0.30
    ✭✭
    -0.30
    截图
    -0.30
    原始内容存档于
    -0.29
    తు
    -0.29
     Lio
    -0.29
    POSITIVE LOGITS
     kasarigan
    0.67
    xase
    0.49
     préférences
    0.47
     HFILL
    0.46
     iParam
    0.46
    InputTagHelper
    0.46
     doInBackground
    0.45
    Personendaten
    0.45
     ddelweddau
    0.44
     createState
    0.44
    Act Density 0.141%

    No Known Activations