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

    Neuronpedia

    INDEX
    Explanations

    suggestive words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fab
    0.47
     Phase
    0.44
     Prod
    0.44
    ibernate
    0.44
     gravitational
    0.43
     prefab
    0.43
     Sa
    0.42
     Proto
    0.42
     Decorative
    0.42
     Bac
    0.42
    POSITIVE LOGITS
    डेंट
    0.51
    mettre
    0.47
    ਨਾ
    0.47
     ಅಭಿಮಾನ
    0.46
     étamines
    0.44
    ,//
    0.44
    ार्टमेंट
    0.44
    ۰۰
    0.43
    হিন্দু
    0.43
     오히려
    0.43
    Act Density 0.004%

    No Known Activations