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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns and associated locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     diarrhea
    0.47
     choice
    0.43
     affected
    0.40
     preference
    0.39
     saliva
    0.38
     escolha
    0.38
     teeth
    0.37
     desires
    0.37
     discrimination
    0.37
     disapproval
    0.37
    POSITIVE LOGITS
    身边
    0.61
     beck
    0.55
     doorstep
    0.47
     side
    0.46
     corner
    0.46
     hip
    0.46
     horizonte
    0.42
     Side
    0.41
     door
    0.41
     horizon
    0.41
    Act Density 0.010%

    No Known Activations