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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a defining role or function

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

    serves as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.75
    \{\\
    -0.66
    ########.
    -0.66
     autorytatywna
    -0.65
    IndentedString
    -0.62
    Externí
    -0.62
     témoig
    -0.61
     للمعارف
    -0.59
    Географиясе
    -0.58
     informée
    -0.58
    POSITIVE LOGITS
     serves
    0.50
     serve
    0.42
     basis
    0.42
    Serves
    0.40
     accessible
    0.39
     effective
    0.39
     serving
    0.38
     served
    0.38
     proper
    0.38
     a
    0.37
    Act Density 0.016%

    No Known Activations