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

    Neuronpedia

    INDEX
    Explanations

    zip file operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     साग
    0.48
     medulla
    0.46
     Tvam
    0.45
     landlab
    0.40
     beteg
    0.40
     поверну
    0.40
     retom
    0.39
     Daim
    0.39
     Stella
    0.38
     acert
    0.38
    POSITIVE LOGITS
    Zip
    0.94
    zip
    0.89
     Zip
    0.89
     zip
    0.86
     ZIP
    0.86
    ZIP
    0.82
    jszip
    0.82
     zipper
    0.79
     unzip
    0.70
     zippers
    0.69
    Act Density 0.003%

    No Known Activations