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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SENSOR
    -0.07
    -de
    -0.07
    Maintenance
    -0.07
    加工
    -0.07
     Walters
    -0.07
     missionary
    -0.06
     कब
    -0.06
     Sv
    -0.06
    aintenance
    -0.06
    .fa
    -0.06
    POSITIVE LOGITS
    %;
↵
    0.07
    imilar
    0.06
    χα
    0.06
     celý
    0.06
     mük
    0.06
    Perl
    0.06
    uffix
    0.06
     格
    0.06
    рогра
    0.06
    erif
    0.06
    Act Density 0.035%

    No Known Activations