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

    Neuronpedia

    INDEX
    Explanations

    keywords related to file handling and programming functions

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

    Code snippets with brackets and parentheses

    np_acts-logits-general · gemini-2.0-flash

    function calls and declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Efq
    -1.35
     $_"
    -1.34
     $_(
    -1.32
    ſelves
    -1.31
     ſind
    -1.29
     Anſ
    -1.28
     iſt
    -1.27
     Majefty
    -1.27
    -1.26
    AsUp
    -1.25
    POSITIVE LOGITS
      
    1.10
       
    0.79
     
    0.78
     ,
    0.77
     my
    0.64
        
    0.58
     My
    0.57
    (
    0.57
     .
    0.57
    _
    0.56
    Act Density 0.677%

    No Known Activations