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

    Neuronpedia

    INDEX
    Explanations

    `healthcare` `insurance` `plan` `systems`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    症
    1.11
    但
    1.09
    })}
    1.09
    이란
    1.05
    我
    1.05
     eiusmod
    1.05
    didReceive
    1.03
    🧪
    1.02
    而且
    1.02
     nt
    1.02
    POSITIVE LOGITS
    𝗕
    1.17
    ма
    1.11
     transpired
    1.11
    ى
    1.11
     vendidos
    1.10
     Buscar
    1.09
     eben
    1.08
    THING
    1.08
    utilizzo
    1.08
    etheless
    1.05
    Act Density 0.035%

    No Known Activations