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

    Neuronpedia

    INDEX
    Explanations

    variations of the verb "say."

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

    what is said

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ***!
    -0.37
     detener
    -0.34
     a
    -0.34
     старости
    -0.32
    modelBuilder
    -0.31
    ✨:
    -0.31
     capuz
    -0.30
     Gauthier
    -0.30
     mukana
    -0.29
    Ohne
    -0.29
    POSITIVE LOGITS
    DeleteCommand
    0.59
     uParam
    0.59
    MLLoader
    0.56
    onAttach
    0.56
     MaterialApp
    0.56
     vVar
    0.56
    MessageWindow
    0.54
     '{}
    0.54
    SqlClient
    0.54
    cshtml
    0.54
    Act Density 0.013%

    No Known Activations