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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indirectly related to methods or processes and their effects

    oai_token-act-pair · gemini-2.0-flash

    way

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     
    -0.71
     autorytatywna
    -0.63
      
    -0.62
    Behaviors
    -0.58
    ↵↵
    -0.57
     ubica
    -0.52
    1
    -0.51
     Neben
    -0.50
     corde
    -0.49
     koke
    -0.49
    POSITIVE LOGITS
    XmlAccessType
    0.89
     Wikimedijinoj
    0.79
     *)__
    0.75
    NUMX
    0.74
    ChildScrollView
    0.74
     ***/
    0.72
    ंदीखरीदारी
    0.72
     (£
    0.69
     Forumite
    0.69
     organise
    0.69
    Act Density 2.486%

    No Known Activations