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

    Neuronpedia

    INDEX
    Explanations

    instances of whitespace characters or empty strings in the text

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

    protected code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.72
    帖最后由
    -0.69
     defaultstate
    -0.66
    Personensuche
    -0.65
     Paglinawan
    -0.64
    SourceChecksum
    -0.63
     otomatig
    -0.61
     protoimpl
    -0.60
    蚪
    -0.59
    ValueStyle
    -0.59
    POSITIVE LOGITS
        
    0.42
       
    0.39
         
    0.37
           
    0.37
    ↵
    0.37
     Rosenthal
    0.36
    Tr
    0.36
    -
    0.36
                         
    0.35
          
    0.35
    Act Density 0.021%

    No Known Activations