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

    Neuronpedia

    INDEX
    Explanations

    attraction and connection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     přev
    0.66
     Au
    0.64
     intervened
    0.62
     சொல்லி
    0.62
     মুছে
    0.62
    Tissue
    0.61
    client
    0.60
     denunci
    0.60
     hospice
    0.60
     اليس
    0.59
    POSITIVE LOGITS
     attraction
    1.18
     attractiveness
    1.07
     attract
    1.05
     attracted
    1.00
     attracting
    1.00
     attracts
    0.99
     Attraction
    0.98
     আকর্ষণীয়
    0.96
     attractions
    0.94
     personality
    0.94
    Act Density 0.103%

    No Known Activations