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

    Neuronpedia

    INDEX
    Explanations

    children

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DICT
    -0.07
    verbatim
    -0.07
    анны
    -0.07
    .ACTION
    -0.06
     search
    -0.06
     Variables
    -0.06
    zeros
    -0.06
    _statistics
    -0.06
    ↵  ↵
    -0.06
    (bundle
    -0.06
    POSITIVE LOGITS
     {{$
    0.07
     Hav
    0.07
    )));
    0.06
     cess
    0.06
    %@
    0.06
     Kash
    0.06
    Prov
    0.06
     Payne
    0.06
     Intelli
    0.06
     {|
    0.06
    Act Density 0.024%

    No Known Activations