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

    Neuronpedia

    INDEX
    Explanations

    a + highly significant word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     অবা
    0.43
     endless
    0.40
    😋
    0.40
     Lovely
    0.39
    Trusted
    0.38
     Favorite
    0.38
    ۜ
    0.38
     मस्त
    0.37
     తయ
    0.37
     Assets
    0.36
    POSITIVE LOGITS
     landmark
    2.00
     momentous
    1.91
     milestone
    1.77
     revolutionary
    1.77
     groundbreaking
    1.73
     breakthrough
    1.70
     monumental
    1.56
    landmark
    1.56
     pivotal
    1.54
    revolutionary
    1.52
    Act Density 0.091%

    No Known Activations