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

    Neuronpedia

    INDEX
    Explanations

    references to lists and items within those lists

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

    list of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    textColor
    -0.31
    ↵↵
    -0.29
     нар
    -0.28
    PDOException
    -0.28
    を迎
    -0.28
    clearTimeout
    -0.28
     shy
    -0.27
     
    -0.27
     nul
    -0.27
    TM
    -0.27
    POSITIVE LOGITS
     list
    1.70
     lists
    1.48
     lijst
    1.46
     List
    1.43
     Lists
    1.35
     lista
    1.34
     LIST
    1.30
     Liste
    1.27
     liste
    1.27
    list
    1.27
    Act Density 0.205%

    No Known Activations