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

    Neuronpedia

    INDEX
    Explanations

    French language and France

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ეხ
    0.41
    validate
    0.40
     stronghold
    0.40
     customers
    0.40
     shocking
    0.40
     richtigen
    0.39
     Skop
    0.39
     ciudadanos
    0.39
    шни
    0.38
    謃
    0.38
    POSITIVE LOGITS
     프랑
    0.47
    法语
    0.46
     français
    0.46
    Repl
    0.45
     françaises
    0.44
     repl
    0.44
    ttp
    0.44
     France
    0.43
     François
    0.43
     Lire
    0.43
    Act Density 0.002%

    No Known Activations