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

    Neuronpedia

    INDEX
    Explanations

    contexts of enumerated lists or properties

    oai_token-act-pair · gemini-2.0-flash

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     متعلقه
    -1.23
    ValueStyle
    -1.10
     Theſe
    -1.06
     Walkover
    -0.99
     raiſ
    -0.98
     CreateTagHelper
    -0.97
     itſelf
    -0.97
    AddTagHelper
    -0.95
     يتيمه
    -0.94
     חיצוניים
    -0.93
    POSITIVE LOGITS
      
    0.63
     
    0.59
    1
    0.58
       
    0.57
        
    0.56
    ↵
    0.55
     and
    0.54
    2
    0.54
    0
    0.52
    ↵↵
    0.51
    Act Density 2.064%

    No Known Activations