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

    Neuronpedia

    INDEX
    Explanations

    possessive noun phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    imbulkan
    0.65
    farande
    0.64
    ֗
    0.64
    CONTENTS
    0.63
    ▩
    0.63
    exists
    0.63
    acaktır
    0.63
     CONTENTS
    0.63
    jetas
    0.62
    ěla
    0.62
    POSITIVE LOGITS
     latest
    1.40
     foray
    1.27
     newest
    1.18
     penchant
    1.18
     involvement
    1.09
     insistence
    1.09
     commitment
    1.07
     recent
    1.07
     obsession
    1.02
     efforts
    1.00
    Act Density 0.141%

    No Known Activations