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

    Neuronpedia

    INDEX
    Explanations

    meaning manifesting maneuvers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ভূমি
    0.44
    䢌
    0.43
    íd
    0.42
     গাড়ী
    0.42
    lež
    0.42
     গাড়ীতে
    0.41
    ைகள
    0.40
     dizendo
    0.40
    یسی
    0.40
     Gres
    0.40
    POSITIVE LOGITS
     motives
    0.42
     costing
    0.38
     motive
    0.38
     motivation
    0.37
    BOOL
    0.36
     angry
    0.36
     incentive
    0.36
    尽量
    0.36
    dL
    0.35
    很久
    0.35
    Act Density 0.001%

    No Known Activations