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

    Neuronpedia

    INDEX
    Explanations

    your [role/service/possession]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     לך
    0.45
     featuring
    0.45
     Featuring
    0.44
     মাস
    0.43
    Paused
    0.42
    Featuring
    0.42
    featuring
    0.41
    Mask
    0.41
    HAND
    0.41
    Handling
    0.40
    POSITIVE LOGITS
     explain
    0.42
     advisor
    0.42
    ниците
    0.42
     armour
    0.41
     adviser
    0.41
     columnar
    0.40
     Employer
    0.40
     Stu
    0.40
     enemies
    0.39
     Advisor
    0.39
    Act Density 0.013%

    No Known Activations