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

    Neuronpedia

    INDEX
    Explanations

    inventory categories or specific items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    j
    1.27
    mpi
    1.23
    hour
    1.21
    oulli
    1.20
    t
    1.20
    sent
    1.19
    menubar
    1.18
    ে
    1.18
    ר
    1.18
    p
    1.17
    POSITIVE LOGITS
     esquerda
    1.29
     să
    1.04
    ങ്ങളും
    0.97
     bulk
    0.96
    腥
    0.95
     agregó
    0.94
     aumentare
    0.92
     reuni
    0.92
     tomada
    0.91
     sects
    0.90
    Act Density 0.002%

    No Known Activations