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

    Neuronpedia

    INDEX
    Explanations

    personal names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ron
    1.12
    Bob
    1.09
     Dick
    1.09
     Bob
    1.08
     Paddy
    1.07
    Herb
    1.07
     Ron
    1.06
     Jim
    1.06
    Jim
    1.05
    Joe
    1.04
    POSITIVE LOGITS
     recent
    0.62
     fiancé
    0.62
     helpful
    0.60
    aken
    0.60
     controlling
    0.57
     pending
    0.56
     lately
    0.56
     compliment
    0.56
     cycling
    0.55
     signify
    0.55
    Act Density 0.016%

    No Known Activations