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

    Neuronpedia

    INDEX
    Explanations

    positive, endearing, and cute descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    শিল্প
    0.72
    AGMENT
    0.71
    美術館
    0.70
     familles
    0.70
     અનુભ
    0.69
     roślin
    0.68
     MenuItem
    0.67
     vrch
    0.67
    iteritems
    0.67
     steadily
    0.67
    POSITIVE LOGITS
     cute
    1.07
     adorable
    1.03
     quirky
    0.95
    !
    0.94
     cheesy
    0.89
     goofy
    0.85
     nerdy
    0.83
     lucu
    0.82
     Cute
    0.81
     lindos
    0.80
    Act Density 0.004%

    No Known Activations