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

    Neuronpedia

    INDEX
    Explanations

    mixed text sources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hier
    -0.06
     Healthy
    -0.06
     встанов
    -0.06
    %↵
    -0.06
     internals
    -0.06
     직접
    -0.06
    _dll
    -0.06
     geek
    -0.06
     روند
    -0.05
     син
    -0.05
    POSITIVE LOGITS
    .Tree
    0.07
     kvůli
    0.07
     bulb
    0.07
    ron
    0.07
    24
    0.06
    .Addr
    0.06
    Rather
    0.06
     append
    0.06
    Updates
    0.06
     focusing
    0.06
    Act Density 0.000%

    No Known Activations