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

    Neuronpedia

    INDEX
    Explanations

    mentions of official statements, especially those given to the media

    oai_token-act-pair · gemini-2.0-flash

    statements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.94
     ujednoznacz
    -0.84
    rawDesc
    -0.74
     المعيارى
    -0.70
     Vikipedi
    -0.70
    DockStyle
    -0.69
    ſelf
    -0.68
    ConstraintMaker
    -0.68
     lenker
    -0.67
     Reſ
    -0.66
    POSITIVE LOGITS
     released
    0.57
     with
    0.48
    ,
    0.46
    Geplaatst
    0.46
     through
    0.45
     issued
    0.44
     highlighting
    0.43
     launched
    0.43
    .
    0.43
     on
    0.41
    Act Density 3.472%

    No Known Activations