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

    Neuronpedia

    INDEX
    Explanations

    attraction and curiosity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    祝福
    0.77
     Shout
    0.70
     धूमधाम
    0.67
     gewährle
    0.67
     hạnh
    0.67
     multil
    0.66
    пя
    0.66
     smile
    0.65
     खुशखबरी
    0.65
     pérdidas
    0.65
    POSITIVE LOGITS
     intrigued
    2.33
     fascinated
    2.31
     fascination
    2.26
     drawn
    2.21
     attracted
    2.08
     curiosity
    2.07
     captivated
    1.96
     Drawn
    1.88
     curious
    1.84
     fascin
    1.83
    Act Density 0.769%

    No Known Activations