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

    Neuronpedia

    INDEX
    Explanations

    possessive determiners and 's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     efforts
    1.43
     sensibilities
    1.42
     shortcomings
    1.42
     prowess
    1.35
     penchant
    1.31
     willingness
    1.29
     burgeoning
    1.28
     achievements
    1.27
     antics
    1.25
     fortunes
    1.24
    POSITIVE LOGITS
    H
    0.96
    P
    0.96
    W
    0.95
    S
    0.89
    X
    0.88
    I
    0.87
    Z
    0.86
    A
    0.85
    U
    0.83
    C
    0.83
    Act Density 0.071%

    No Known Activations