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

    Neuronpedia

    INDEX
    Explanations

    parts of computer code, especially variable assignments and object creation, sometimes with surrounding text

    oai_token-act-pair · gemini-2.0-flash

    Code/configuration snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.96
     myſelf
    -0.91
     Jefus
    -0.91
     whoſe
    -0.89
     themſelves
    -0.88
     itſelf
    -0.87
     quæ
    -0.87
     greateſt
    -0.86
     Monfieur
    -0.85
     againſt
    -0.85
    POSITIVE LOGITS
    
    0.66
     ligiloj
    0.54
     виправивши
    0.54
     Illuminate
    0.52
     ComVisible
    0.51
     مرئيه
    0.51
    Illuminate
    0.50
     EconPapers
    0.48
    EndGlobalSection
    0.48
    ">//
    0.47
    Act Density 13.314%

    No Known Activations