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

    Neuronpedia

    INDEX
    Explanations

    introducing subsequent points or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rogue
    0.38
     policías
    0.37
     perverse
    0.37
     intractable
    0.37
     demandas
    0.37
     deporte
    0.36
     hielo
    0.36
     biofilms
    0.36
    𝑀
    0.35
     refugi
    0.35
    POSITIVE LOGITS
     Additionally
    0.53
     निम्नलिखित
    0.50
     Furthermore
    0.50
    ina
    0.50
    Furthermore
    0.47
    ßerdem
    0.46
    ess
    0.46
     следующие
    0.46
    actéristiques
    0.46
     Specifically
    0.46
    Act Density 0.798%

    No Known Activations