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

    Neuronpedia

    INDEX
    Explanations

    code and technical documentation with indentation

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -1.44
      
    -0.89
    ,
    -0.67
    frastructure
    -0.65
     the
    -0.64
     a
    -0.59
    attenzione
    -0.58
    *
    -0.57
       
    -0.56
    /*
    -0.56
    POSITIVE LOGITS
     Majefty
    0.86
     
    0.81
    HtmlAttribute
    0.80
     Diſ
    0.79
     Wikispecies
    0.79
     ―――――
    0.79
    ſelves
    0.78
    PreferredItem
    0.77
    Rhestr
    0.76
     
    0.76
    Act Density 3.787%

    No Known Activations