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

    Neuronpedia

    INDEX
    Explanations

    de

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -flow
    -0.08
    npj
    -0.06
    ylim
    -0.06
     bulld
    -0.06
     hlavu
    -0.06
    _help
    -0.06
    ISC
    -0.06
    youtu
    -0.06
    _MD
    -0.06
    หว
    -0.06
    POSITIVE LOGITS
     κά
    0.06
     Afghan
    0.06
     UNC
    0.06
     enjoyed
    0.06
    	required
    0.06
     ще
    0.06
     propose
    0.06
     ferry
    0.06
    ابقه
    0.06
    Configure
    0.06
    Act Density 0.061%

    No Known Activations