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

    Neuronpedia

    INDEX
    Explanations

    essay requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sklär
    0.52
    shah
    0.50
    drying
    0.49
    tapping
    0.46
    ('',
    0.45
     कार्ड
    0.45
    ിയും
    0.44
    ាញ
    0.44
    banam
    0.44
    sums
    0.44
    POSITIVE LOGITS
    ים
    0.61
     את
    0.59
     נ
    0.57
     ח
    0.55
     הע
    0.54
     פ
    0.53
    าร
    0.53
     הא
    0.51
     נק
    0.51
     ר
    0.50
    Act Density 0.001%

    No Known Activations