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

    Neuronpedia

    INDEX
    Explanations

    given samples or records

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     policía
    0.46
     trending
    0.45
     Policía
    0.45
     onboarding
    0.45
     smartwatch
    0.44
     Polícia
    0.44
     बचाव
    0.43
     الحكومة
    0.43
     chodzi
    0.43
     želite
    0.43
    POSITIVE LOGITS
     sämt
    0.46
     annotate
    0.46
     각종
    0.44
     পুস্তক
    0.44
     अनेक
    0.44
     alcuna
    0.43
     several
    0.42
    ﺘ
    0.42
     the
    0.42
     столь
    0.42
    Act Density 0.006%

    No Known Activations