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

    Neuronpedia

    INDEX
    Explanations

    people who share interests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     personalization
    0.43
     personalized
    0.39
     Mastering
    0.39
     tomado
    0.38
     Personal
    0.38
    Personal
    0.38
     mastering
    0.38
     Mastery
    0.37
    ategories
    0.36
    ालय
    0.36
    POSITIVE LOGITS
     condivid
    0.86
     understands
    0.72
    共享
    0.72
     partage
    0.72
     compatible
    0.71
     understand
    0.70
     이해
    0.69
     kindred
    0.68
     hasonló
    0.68
     condiv
    0.67
    Act Density 0.029%

    No Known Activations