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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mysteries
    -0.07
    Experimental
    -0.06
     magazines
    -0.06
    ***/↵↵
    -0.06
    (sel
    -0.06
    Kon
    -0.06
    \">↵
    -0.06
    NSMutableDictionary
    -0.06
    .gson
    -0.06
    -source
    -0.06
    POSITIVE LOGITS
     Andrea
    0.07
     大阪
    0.07
    /world
    0.07
     Sistema
    0.07
     Sau
    0.07
     Poh
    0.07
     DWC
    0.07
     Crescent
    0.07
     Đây
    0.06
    rones
    0.06
    Act Density 0.002%

    No Known Activations