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

    Neuronpedia

    INDEX
    Explanations

    describes things as captivating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    د
    1.09
    h
    1.07
    í
    0.94
    ine
    0.84
    ä
    0.79
    دون
    0.79
    ien
    0.79
    مة
    0.78
    ance
    0.77
     proteg
    0.77
    POSITIVE LOGITS
     mesmer
    1.07
     mesmerizing
    1.02
     captivated
    1.00
     hypnotic
    0.89
     hostage
    0.83
     satu
    0.78
     captivating
    0.75
     vulture
    0.74
     Pierws
    0.74
     Почему
    0.73
    Act Density 0.005%

    No Known Activations