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

    Neuronpedia

    INDEX
    Explanations

    code-related comments and documentation

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

    code snippets and comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BorderSide
    -0.77
    يكب
    -0.65
    parsedMessage
    -0.63
    她們
    -0.61
    日閲覧
    -0.61
    majánló
    -0.59
    MessageTagHelper
    -0.57
     الرياضيه
    -0.57
     enfans
    -0.56
    InputBorder
    -0.56
    POSITIVE LOGITS
    
    0.41
     Paglinawan
    0.40
            
    0.39
        
    0.38
    
    0.37
    Marie
    0.36
    

    0.36
    ://
    0.35
    Engineering
    0.34
      
    0.34
    Act Density 0.005%

    No Known Activations