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

    Neuronpedia

    INDEX
    Explanations

    code-related syntax and structure, particularly focusing on programming language constructs

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

    Code snippets

    np_acts-logits-general · gemini-2.0-flash

    code structure and strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.61
     ”,
    -0.46
     (−
    -0.45
     üç
    -0.45
     användas
    -0.43
    3
    -0.42
    ster
    -0.42
     "_"
    -0.41
     tarko
    -0.41
    agn
    -0.41
    POSITIVE LOGITS
        
    1.66
    enumi
    0.86
     beginnetje
    0.84
     EconPapers
    0.80
         
    0.76
       
    0.75
    BufferException
    0.74
    awtextra
    0.73
     linkovi
    0.71
    __':
    0.69
    Act Density 0.031%

    No Known Activations