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

    Neuronpedia

    INDEX
    Explanations

    https:// links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     poo
    0.69
     aeruginosa
    0.68
     Leroy
    0.64
    skog
    0.62
     Monro
    0.62
    arbit
    0.62
     Sart
    0.60
     pointed
    0.59
     Deserialize
    0.57
    marginal
    0.57
    POSITIVE LOGITS
    ]---
    0.68
     úspě
    0.68
     यशस्वी
    0.66
     productive
    0.65
    成功的
    0.65
     نتائج
    0.64
    árias
    0.63
     koristi
    0.61
    竟
    0.60
     conclusión
    0.60
    Act Density 0.031%

    No Known Activations