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

    Neuronpedia

    INDEX
    Explanations

    titles, tests, meat, positive impact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     geos
    0.46
    㓦
    0.46
     transacción
    0.44
     jaane
    0.44
     disgraceful
    0.44
    VENUE
    0.44
     deset
    0.43
     څه
    0.43
     krás
    0.43
     nélkül
    0.43
    POSITIVE LOGITS
     Exclusive
    0.45
     Investigators
    0.43
     Plants
    0.42
    Choices
    0.41
     Account
    0.41
    0.39
     Announcement
    0.39
     Scholar
    0.38
     Leak
    0.38
    <i>
    0.38
    Act Density 7.659%

    No Known Activations