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

    Neuronpedia

    INDEX
    Explanations

    filename and Khan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Weiss
    0.75
     Silicone
    0.74
     LES
    0.73
     Maas
    0.73
     कार्
    0.72
     CP
    0.72
     Mas
    0.71
     Twin
    0.69
    鹿
    0.68
     Maia
    0.67
    POSITIVE LOGITS
    filename
    0.84
    Khan
    0.81
     शाहरुख
    0.80
     Khan
    0.78
    Filename
    0.77
     filename
    0.77
    schema
    0.75
     schema
    0.72
    filenames
    0.70
    khan
    0.69
    Act Density 0.227%

    No Known Activations