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

    Neuronpedia

    INDEX
    Explanations

    significant numbers, particularly in the context of data or statistics

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

    examples in multiple languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PopupWindow
    -0.48
     AppCompatTheme
    -0.45
     EconPapers
    -0.44
     $_"
    -0.42
     mechanism
    -0.42
    '])){
    -0.42
    хьтан
    -0.41
    AnchorStyles
    -0.41
     mécan
    -0.40
    انجليز
    -0.40
    POSITIVE LOGITS
    #+#
    0.61
    Beispiele
    0.50
     Beispiele
    0.48
    principalColumn
    0.48
     examples
    0.46
    Examples
    0.45
    GeneratedMessage
    0.45
     Contoh
    0.44
     exemples
    0.44
     Examples
    0.43
    Act Density 0.323%

    No Known Activations